fix(deps): lift btcd off the vulnerable v0.22.3 downgrade pin

[mswilkison]

Summary

go.mod replaces the whole btcd module with v0.22.3 - below the v0.23.2 the module itself requires - which keeps three already-fixed security advisories open against the Bitcoin consensus, wire, and script packages the bridge actually compiles. (Three vulnerabilities, six identifiers counting the GHSA aliases.)

go.mod  github.com/btcsuite/btcd v0.23.2                              // require
go.mod  github.com/btcsuite/btcd => github.com/btcsuite/btcd v0.22.3  // replace — wins

This is long-standing on main and not specific to any release branch. It surfaced during a dependency sweep of #4109; that PR's integration branch inherits it, and this fix is deliberately targeted here rather than stacked on the release candidate so it gets CI and normal review.

Unlike an unused-code advisory, this code is in the build — go list -deps ./... returns 16 btcsuite/btcd packages including blockchain, blockchain/indexers, btcjson, btcutil, txscript, and wire.

Advisory	Package	Fixed in	Status before	After
GO-2022-1098 / GHSA-2chg-86hq-7w38 — DoS in message decoding, witness size checking	wire	0.23.2	open (below the repo's own require)	fixed
GO-2024-2818 / GHSA-3jgf-r68h-xfqm — consensus failures	blockchain, txscript	0.24.0	open	fixed
GO-2024-3189 / GHSA-27vh-h6mc-q6g8 — incorrect FindAndDelete re-implementation	txscript	0.24.2-beta.rc1	open	fixed

Why the downgrade was there, and why it can go

btcd v0.23 extracted btcd/btcec into the separate module btcd/btcec/v2, and later versions don't ship the pre-split package at all. Two consumers still import the pre-split path and can't simply be edited: the pinned tss-lib fork (crypto/ckd, tss/curve) and first-party key-handling code (pkg/crypto/ephemeral, pkg/crypto/secp256k1, pkg/net/..., pkg/chain/local_v1, pkg/internal/pbutils), which relies on v1 btcec types being aliases of the crypto/ecdsa types.

So one crypto package was holding the entire module — consensus code included - a minor version back.

This PR serves just that package from an in-tree copy of the btcd v0.22.3 btcec sources (third_party/btcsuite/btcec) and moves the module itself to v0.24.2. The vendored copy is byte-identical to upstream apart from a mechanical gofmt pass; VENDOR.md records provenance, a reproducible diff -r verification recipe, and the exit path (delete the directory once tss-lib migrates to btcec/v2). The upstream btcec test suite ships with it and passes.

Why v0.24.2 and not v0.26.2

v0.24.2 is the lowest version that fixes all three advisories (the last one lands in 0.24.2-beta.rc1), and going higher isn't currently possible:

• v0.25.0 requires btcec/v2 v2.3.5, and btcec/v2 v2.3.4 changed ecdsa.SignCompact from ([]byte, error) to []byte. go-ethereum v1.13.15 calls the two-value form in crypto/signature_nocgo.go, so pulling btcec/v2 that far forward breaks every cgo-less build - including the cross-compiled release binaries that make release produces. Raising btcd past v0.24.2 requires upgrading go-ethereum first, which is out of scope here.
• v0.26 additionally restructured btcd: wire, txscript, chaincfg, chainhash, and btcutil moved to separate /v2 modules and the plain-path packages no longer exist. The go-electrum and tss-lib forks import the plain paths with import strings we don't control, so v0.26.x isn't reachable without forking both.

So this is a compatibility ceiling, not a security gap - v0.24.2 is advisory-clean. Both constraints are recorded in the go.mod comment so the next person to touch this pin doesn't have to rediscover them.

The btcd/v2 alias goes too

replace github.com/btcsuite/btcd/v2 => github.com/btcsuite/btcd v0.23.4 only isolates self-contained packages. Any aliased package that imports a sibling btcd package does so by plain path, which resolved back to the v0.22.3 module - so the "patched" alias was linking vulnerable wire/txscript underneath it. With the downgrade gone the alias has no purpose, and the two pkg/bitcoin/electrum files using it return to plain paths.

First-party fallout

• txscript.NewTxSigHashes takes a PrevOutputFetcher since v0.23 and (as of v0.24.2) requires the previous outputs of all inputs. TransactionBuilder now registers each input's locking script and value in a MultiPrevOutFetcher as inputs are added - it already fetched exactly that data for its sighash args. ComputeSignatureHashes also asserts the set is complete and returns an error, rather than letting a future gap reach the panicking path.
• mempool.GetTxVirtualSize / btcutil.Hash160 / btcutil.NewTx move from the archived btcsuite/btcutil to btcd/btcutil (same semantics).

Deserialization cap and recover - required by the version jump

btcd v0.24.2 rewrote MsgTx.btcDecode to slice every script of a transaction out of one fixed-size 4 MiB buffer (scriptSlabSize = 1 << 22), advancing it after each read. readScriptBuf bounds each individual script against maxWitnessItemSize but never against the remaining buffer, so once the cumulative script length of a single transaction passes 4 MiB the next slice panics instead of returning an error:

panic: runtime error: slice bounds out of range [:900000] with capacity 594304
  btcd@v0.24.2/wire/msgtx.go:1041  readScriptBuf
  ...
  pkg/bitcoin/transaction.go       (*Transaction).Deserialize

Reproduced directly: 4 × 900 KB output scripts decode cleanly, 5 panic. Both decoders this PR replaces (v0.22.3 and the v0.23.4 alias) allocate per script and handle the same bytes fine, so this would be a regression introduced by the upgrade - on a path fed by the untrusted Electrum backend. decodeTransaction runs before GetTransaction's txid check, GetTransactionConfirmations performs no hash check at all, and no recover() covers the tbtc signing paths, so it would terminate the node. Upstream fixed it only in the split-out wire/v2 module, part of the v0.26 layout the plain-path forks make unreachable.

The fix is two layers, and only the combination closes the panic: a MaxTransactionByteLength = 4_000_000 cap applied in bitcoin.Transaction.Deserialize and electrum.decodeTransaction (a transaction's weight is 3*base_size + total_size and cannot exceed the 4,000,000 WU maximum block weight, so a consensus-valid transaction is always strictly shorter than the cap - nothing legitimate is rejected), plus a recover() that turns the slice-bounds panic that can still fire below the cap into a plain error. Two regression tests (TestTransaction_DeserializeDeclaredNotDelivered and TestDecodeTransactionDeclaredNotDelivered, both added in 626538d2) construct a 194,378-byte (189.8 KiB, 4.86% of the cap) transaction that panics in unpatched btcd and confirm the recover() returns the error. The cap alone is not sufficient - without the recover(), payloads of that size terminate the process. The cap bounds grossly oversized input; the recover() is what actually turns the under-cap panic into an error.

A subsequent commit also pre-checks len(rawTx)/2 against MaxTransactionByteLength in electrum.decodeTransaction before hex.DecodeString allocates, so a malicious multi-GB hex string can't pay the full allocation before the guard runs.

Note: the recover() covers slice-bounds panics from readScriptBuf only. It does not cover fatal runtime errors such as out-of-memory from attacker-declared varint counts that btcd's wire decoder honors before reading backing bytes. Closing that class of input requires either a pre-decode budget check on declared input/output counts or a future btcd release; both are out of scope here.

The v0.22.3-to-v0.24.2 jump also changes btcd's script-decoding internals beyond the slab panic. Two material changes worth knowing for future triage:

• The shared script free-list ceiling rises from 6.4 MB globally (12,500 × 512 B entries) to roughly 524 MB globally (125 × 4 MiB slabs) - a ~82× increase, not ~8000× (the earlier draft conflated bytes-per-entry with bytes-per-slab). Per-decode worst case becomes one 4 MiB slab (v0.22.3 allocated per script); only the global retention grows.
• The per-script cap tightens from 32 MiB (MaxMessagePayload) to 4,000,000 (maxWitnessItemSize) - strictly safer, no legitimate transaction is affected.

Neither is a security issue; both are documented in the corresponding MaxTransactionByteLength doc comment and in VENDOR.md.

Docker

third_party/ is copied before RUN go mod download. The directory replace target must exist for the module graph to resolve, so the image build would otherwise fail at that step even though local builds pass.

Verification

• go build ./..., gofmt -l . clean; full go test ./... green.
• CGO_ENABLED=0 go build for darwin/amd64, darwin/arm64, linux/amd64, linux/arm64, windows/amd64 - the cgo-less cross-compile path make release uses, which selects go-ethereum's signature_nocgo.go and is where the btcec/v2 incompatibility above shows up.
• go vet ./... reports only the pre-existing pkg/tecdsa/signing/protocol.go copylock warning, byte-identical on unmodified main.
• TestTransactionBuilder_Signing byte-vector fixtures pass: DER signatures, sighashes, and compressed public keys are byte-identical across the version jump. The signing path still uses v1 btcec (now vendored, byte-identical), so its implicit BIP-62 low-S normalization is preserved.
• Vendored-copy identity verified via the VENDOR.md recipe: only the four added files (go.mod, go.sum, LICENSE, VENDOR.md) differ from gofmt'd upstream btcec@v0.22.3.
• docker build --target build-sources passes, including the go mod download step that fails without the third_party COPY.
• Panic reproduced before the fix and confirmed to return a clean error after.

Known residuals

• The archived github.com/btcsuite/btcutil (2019) is still linked, because the tss-lib fork's crypto/ckd imports its base58 package - the same unchangeable-import-string constraint that motivates the vendoring. One pure codec package, no advisories against it; first-party code no longer touches it. MVS now selects an ~20-months-older btcsuite/btcutil pseudo-version than main did (the archived v1.0.3-0.20201208143702 direct require is gone, replaced by the tss-lib fork's v0.0.0-20190425235716-9e5f4b9a998d); the only compiled package (base58) is functionally identical between the two commits, so this is benign.
• go.sum keeps /go.mod-only hash lines for two old btcd pseudo-versions reached through transitive requires that MVS overrides. No h1: hashes, so no source is compiled; the vulnerable v0.22.3/v0.23.4 full hashes are gone. Naive graph-level SCA tools may still surface them.
• The vendored btcec sits at a module path OSV doesn't index, so a hypothetical future advisory against pre-split btcec code wouldn't be flagged automatically. None of the current three are in btcec. The vendored dir is also invisible to root-module go test ./... and has no automated advisory monitor; byte-identity relies on a human running the VENDOR.md recipe.
• The versionless directory replace means external modules importing keep-core packages can't resolve the btcec requirement. Not a new blast radius: main already carries the same unresolvable-with-replace pattern for google.golang.org/protobuf/dev, which downstream consumers cannot resolve either. The btcec pseudo-version is new on this branch, but the underlying pattern is pre-existing.

Test plan

• go build ./... / go vet ./... / gofmt -l .
• go test ./... (full suite)
• Vendored btcec upstream test suite, from the main module and standalone
• VENDOR.md byte-identity verification recipe
• docker build --target build-sources
• CI green on this branch

Note for #4109

The security-release integration branch carries the same downgrade. Once this lands, its next rebase picks the fix up; the go.mod resolution there is mechanical (that branch has a much newer dependency set, so the conflict is in surrounding lines rather than the btcd ones).

Summary by CodeRabbit

• Bug Fixes

  • Bitcoin transaction decoding now rejects oversized data and returns errors instead of crashing on malformed input.
  • Signature-hash generation now reports missing previous transaction outputs.
  • Updated Bitcoin cryptography support improves compatibility and dependency resolution.

• Security

  • Added secp256k1 key, signature, encryption, and decryption capabilities with validation safeguards.

• Tests

  • Expanded coverage for transaction handling, cryptographic operations, key parsing, signatures, and error scenarios.

[coderabbitai]

Warning

Review limit reached

@piotr-roslaniec, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 38 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: fbc85fc7-786b-43f7-9279-d4a7b3c47b27

📥 Commits

Reviewing files that changed from the base of the PR and between 69da1aa and d0a2025.

📒 Files selected for processing (2)

• .github/workflows/client.yml
• third_party/btcsuite/btcec/VENDOR.md

📝 Walkthrough

Walkthrough

The change updates Bitcoin dependency resolution, vendors the btcec secp256k1 implementation, adds transaction-size and witness sighash safeguards, and introduces cryptographic key, signature, and encryption functionality with comprehensive tests and examples.

Changes

Bitcoin dependency and transaction handling

Layer / File(s)	Summary
Dependency wiring and transaction safeguards Dockerfile, go.mod, pkg/bitcoin/...	Docker builds include the vendored replacement module; Bitcoin imports and versions are aligned; transaction deserialization enforces size and panic safeguards; transaction builders register previous outputs for witness signature hashing.

Vendored btcec implementation

Layer / File(s)	Summary
Vendored secp256k1 arithmetic and curve implementation third_party/btcsuite/btcec/...	Adds field arithmetic, Jacobian curve operations, scalar multiplication, precomputation, generators, benchmarks, tests, licensing, and vendoring documentation.

Key and signature APIs

Layer / File(s)	Summary
Key, public-key, and signature APIs third_party/btcsuite/btcec/privkey.go, pubkey.go, signature.go, *_test.go	Adds private-key serialization and signing, public-key parsing and serialization, DER signatures, compact signature recovery, and RFC6979 deterministic signing with test vectors.

Encryption and examples

Layer / File(s)	Summary
ECDH encryption and package examples third_party/btcsuite/btcec/ciphering.go, ciphering_test.go, doc.go, example_test.go	Adds shared-secret derivation, AES-CBC encryption, HMAC verification, PKCS#7 padding, malformed-input tests, documentation, and usage examples.

Estimated code review effort: 5 (Critical) | ~120 minutes

Sequence Diagram(s)

sequenceDiagram
  participant Sender
  participant Encrypt
  participant Recipient
  participant Decrypt
  Sender->>Encrypt: plaintext and recipient public key
  Encrypt->>Recipient: ephemeral public key, IV, ciphertext, and HMAC
  Recipient->>Decrypt: ciphertext and private key
  Decrypt->>Recipient: authenticated plaintext

Loading

Suggested reviewers: lionakhnazarov, piotr-roslaniec

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 70.75% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately summarizes the main dependency update: removing the vulnerable btcd downgrade pin and raising btcd to a newer version.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands.}

[coderabbitai]

Actionable comments posted: 3

🧹 Nitpick comments (1)

pkg/bitcoin/electrum/transaction.go (1)

21-31: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low value

Consider extracting the size guard into a shared pkg/bitcoin helper.

The check and error text are byte-for-byte duplicates of Transaction.Deserialize (pkg/bitcoin/transaction.go Lines 166-173). A single exported validator keeps the limit and message in sync if either changes.

♻️ Sketch

In pkg/bitcoin/transaction.go:

// ValidateTransactionByteLength returns an error if data exceeds the maximum
// transaction byte length accepted by the decoder.
func ValidateTransactionByteLength(length int) error {
	if length > MaxTransactionByteLength {
		return fmt.Errorf(
			"transaction byte length [%v] exceeds the maximum of [%v]",
			length,
			MaxTransactionByteLength,
		)
	}
	return nil
}

Then here:

-	if len(headerBytes) > bitcoin.MaxTransactionByteLength {
-		return nil, fmt.Errorf(
-			"transaction byte length [%v] exceeds the maximum of [%v]",
-			len(headerBytes),
-			bitcoin.MaxTransactionByteLength,
-		)
-	}
+	if err := bitcoin.ValidateTransactionByteLength(len(headerBytes)); err != nil {
+		return nil, err
+	}

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@pkg/bitcoin/electrum/transaction.go` around lines 21 - 31, Extract the
duplicated transaction-size check into an exported ValidateTransactionByteLength
helper in the bitcoin package, preserving the existing limit and error text.
Update both Transaction.Deserialize and the Electrum deserialization path to
call this shared validator and return its error unchanged.

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@third_party/btcsuite/btcec/example_test.go`:
- Around line 7-13: Add an explicit go test ./third_party/btcsuite/btcec/...
step to the applicable Go test workflow(s), ensuring the vendored btcec examples
run under CI alongside the existing root-module gotestsum coverage. Reuse the
current workflow setup and apply this to every release/client Go test workflow
that needs the coverage.

In `@third_party/btcsuite/btcec/VENDOR.md`:
- Around line 43-65: Add and maintain the root go.sum entry for the locally
replaced module github.com/btcsuite/btcd/btcec at the synthetic version declared
by its go.mod. Ensure the entry is generated or preserved when running go mod
tidy with the local module replacement, while leaving the existing btcec/v2
entries unchanged.
- Around line 5-13: Update the introductory file-count statement in VENDOR.md to
say four files are added for vendoring only, matching the existing “four added
files” wording later in the document.

---

Nitpick comments:
In `@pkg/bitcoin/electrum/transaction.go`:
- Around line 21-31: Extract the duplicated transaction-size check into an
exported ValidateTransactionByteLength helper in the bitcoin package, preserving
the existing limit and error text. Update both Transaction.Deserialize and the
Electrum deserialization path to call this shared validator and return its error
unchanged.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: 7d679d6b-6bed-4ad4-990c-9eefde39c7b0

📥 Commits

Reviewing files that changed from the base of the PR and between 6f87e20 and 245eb9f.

⛔ Files ignored due to path filters (2)

• go.sum is excluded by !**/*.sum
• third_party/btcsuite/btcec/go.sum is excluded by !**/*.sum

📒 Files selected for processing (32)

• Dockerfile
• go.mod
• pkg/bitcoin/electrum/block.go
• pkg/bitcoin/electrum/transaction.go
• pkg/bitcoin/estimator.go
• pkg/bitcoin/script.go
• pkg/bitcoin/transaction.go
• pkg/bitcoin/transaction_builder.go
• pkg/bitcoin/transaction_test.go
• third_party/btcsuite/btcec/LICENSE
• third_party/btcsuite/btcec/README.md
• third_party/btcsuite/btcec/VENDOR.md
• third_party/btcsuite/btcec/bench_test.go
• third_party/btcsuite/btcec/btcec.go
• third_party/btcsuite/btcec/btcec_test.go
• third_party/btcsuite/btcec/ciphering.go
• third_party/btcsuite/btcec/ciphering_test.go
• third_party/btcsuite/btcec/doc.go
• third_party/btcsuite/btcec/example_test.go
• third_party/btcsuite/btcec/field.go
• third_party/btcsuite/btcec/field_test.go
• third_party/btcsuite/btcec/genprecomps.go
• third_party/btcsuite/btcec/gensecp256k1.go
• third_party/btcsuite/btcec/go.mod
• third_party/btcsuite/btcec/precompute.go
• third_party/btcsuite/btcec/privkey.go
• third_party/btcsuite/btcec/privkey_test.go
• third_party/btcsuite/btcec/pubkey.go
• third_party/btcsuite/btcec/pubkey_test.go
• third_party/btcsuite/btcec/secp256k1.go
• third_party/btcsuite/btcec/signature.go
• third_party/btcsuite/btcec/signature_test.go

[coderabbitai]

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Inspect the vendored module manifest and root replace directives.
fd -t f 'go.mod' | while read -r f; do echo "=== $f ==="; cat "$f"; done

# Check root module's replace/require wiring for btcec.
rg -n 'btcec|btcd' go.mod go.sum 2>/dev/null | head -50

# Does CI run tests inside third_party?
fd -t f -e yml -e yaml . .github 2>/dev/null --exec sh -c 'echo "=== $1 ==="; cat "$1"' sh {}
rg -n 'go test|third_party' Makefile 2>/dev/null

Repository: threshold-network/keep-core

Length of output: 50383

---

🏁 Script executed:

#!/bin/bash
set -euo pipefail

echo "== github workflows mentioning go test/third_party =="
fd -t f -e yml -e yaml . .github | xargs rg -n 'go test|gotestsum|third_party|/btcec|btcec' || true

echo "== Dockerfiles mentioning go modules/tests == "
fd -t f 'Dockerfile*' . | while read -r f; do
  echo "--- $f"
  rg -n 'WORKDIR|go test|gotestsum|go mod|third_party|/btcec|btcec' "$f" || true
done

echo "== candidate files under btcec =="
fd -t f . third_party/btcsuite/btcec | sort

echo "== btcec module imports/requirements relevant lines =="
sed -n '1,80p' third_party/btcsuite/btcec/go.mod
sed -n '1,40p' third_party/btcsuite/btcec/example_test.go
sed -n '1,40p' third_party/btcsuite/btcec/VENDOR.md

Repository: threshold-network/keep-core

Length of output: 5882

---

🏁 Script executed:

#!/bin/bash
set -euo pipefail

echo "== Dockerfile build dependencies section =="
sed -n '1,100p' Dockerfile

echo "== go.mod tidy/replace dependency section =="
sed -n '60,105p' go.mod

echo "== check presence of btcec go.sum checksums =="
rg -n 'github.com/btcsuite/btcd/btcec|github.com/btcsuite/btcd/chaincfg/chainhash|github.com/davecgh/go-spew' third_party/btcsuite/btcec/go.sum go.sum

Repository: threshold-network/keep-core

Length of output: 6936

---

Run the vendored btcec examples in CI.

The module wiring is already correct: github.com/btcsuite/btcd/btcec is explicitly required and replaced with ./third_party/btcsuite/btcec, and go.mod also requires github.com/btcsuite/btcd/chaincfg/chainhash with matching checksums. The remaining CI gap is that release/client gotestsum -- ./... runs from the root module, so the standalone btcec sub-module examples remain uncovered. Add an explicit go test ./third_party/btcsuite/btcec/... step in the Go test workflow(s).

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@third_party/btcsuite/btcec/example_test.go` around lines 7 - 13, Add an
explicit go test ./third_party/btcsuite/btcec/... step to the applicable Go test
workflow(s), ensuring the vendored btcec examples run under CI alongside the
existing root-module gotestsum coverage. Reuse the current workflow setup and
apply this to every release/client Go test workflow that needs the coverage.

[mswilkison]

CI is green (21/21). One correction to the version choice above, worth recording since it constrains any future btcd bump.

The first push used btcd v0.25.0 and client-build-test-publish failed:

signature_nocgo.go:85:14: assignment mismatch: 2 variables but btc_ecdsa.SignCompact returns 1 value

v0.25.0 requires btcec/v2 v2.3.5, and v2.3.4 changed ecdsa.SignCompact from ([]byte, error) to []byte. go-ethereum v1.13.15 calls the two-value form in crypto/signature_nocgo.go — the file selected when cgo is disabled, i.e. exactly the cross-compiled release binaries make release produces. Nothing on the cgo path is affected, which is why it passed local builds, go vet, the full test suite, and a docker build --target build-sources (the cross-compile lives in the later build-bins stage).

Now pinned to v0.24.2, which requires btcec/v2 v2.1.3 so MVS leaves it at v2.2.0. All three advisories remain cleared — v0.24.2 is the release that fixes the last of them (GO-2024-3189, in 0.24.2-beta.rc1).

That makes the pin exact in both directions: it can't go lower without reopening an advisory, or higher without upgrading go-ethereum first. Both constraints are in the go.mod comment. Verified with CGO_ENABLED=0 go build across darwin/amd64, darwin/arm64, linux/amd64, linux/arm64, windows/amd64 — and confirmed the old pin reproduces the CI error under the same check, so it's a real regression test rather than an assumption.

Note for whoever rebases security-release/candidate-1: that branch carries go-ethereum v1.17.3, so it tolerates v0.25.0 and could go higher — but v0.24.2 is advisory-clean there too, so the merge needs no adjustment.

[lrsaturnino]

Reviewed the btcd downgrade pin and found one issue, now fixed:

MaxTransactionByteLength cap does not close the panic it was added for (Critical) — the cap only bounds a transaction's total wire length, but the underlying panic is triggered by the cumulative declared script/witness length within a single transaction exceeding btcd's shared, fixed-size 4,194,304-byte script buffer. A payload that delivers roughly 194 KB of real script data and then merely declares, without delivering, one more large item still panics — well under the byte-length cap. Fixed by wrapping both untrusted-input decode paths (bitcoin.Transaction.Deserialize and electrum.decodeTransaction) in a recover() that converts any panic from the underlying btcd decoder into a returned error, correcting the MaxTransactionByteLength doc comment (it implied the length check alone closed this panic), and adding regression tests in both packages covering the minimal reproduction. Commit 626538d.

No other issues found.

[lrsaturnino]

1 finding fixed and pushed; no items requiring manual follow-up.

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@third_party/btcsuite/btcec/README.md`:
- Around line 8-14: Correct the documentation typos in the btcec README: change
“suite of test” to “suite of tests,” fix “signficantly” to “significantly,”
revise “developers original” to the grammatically correct possessive wording,
and correct “parsed form raw bytes” to “parsed from raw bytes” in the additional
affected section.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: 34aeeb4c-8491-4742-87af-22afaef932ed

📥 Commits

Reviewing files that changed from the base of the PR and between 245eb9f and 626538d.

⛔ Files ignored due to path filters (2)

• go.sum is excluded by !**/*.sum
• third_party/btcsuite/btcec/go.sum is excluded by !**/*.sum

📒 Files selected for processing (33)

• Dockerfile
• go.mod
• pkg/bitcoin/electrum/block.go
• pkg/bitcoin/electrum/transaction.go
• pkg/bitcoin/electrum/transaction_test.go
• pkg/bitcoin/estimator.go
• pkg/bitcoin/script.go
• pkg/bitcoin/transaction.go
• pkg/bitcoin/transaction_builder.go
• pkg/bitcoin/transaction_test.go
• third_party/btcsuite/btcec/LICENSE
• third_party/btcsuite/btcec/README.md
• third_party/btcsuite/btcec/VENDOR.md
• third_party/btcsuite/btcec/bench_test.go
• third_party/btcsuite/btcec/btcec.go
• third_party/btcsuite/btcec/btcec_test.go
• third_party/btcsuite/btcec/ciphering.go
• third_party/btcsuite/btcec/ciphering_test.go
• third_party/btcsuite/btcec/doc.go
• third_party/btcsuite/btcec/example_test.go
• third_party/btcsuite/btcec/field.go
• third_party/btcsuite/btcec/field_test.go
• third_party/btcsuite/btcec/genprecomps.go
• third_party/btcsuite/btcec/gensecp256k1.go
• third_party/btcsuite/btcec/go.mod
• third_party/btcsuite/btcec/precompute.go
• third_party/btcsuite/btcec/privkey.go
• third_party/btcsuite/btcec/privkey_test.go
• third_party/btcsuite/btcec/pubkey.go
• third_party/btcsuite/btcec/pubkey_test.go
• third_party/btcsuite/btcec/secp256k1.go
• third_party/btcsuite/btcec/signature.go
• third_party/btcsuite/btcec/signature_test.go

🚧 Files skipped from review as they are similar to previous changes (23)

• third_party/btcsuite/btcec/go.mod
• third_party/btcsuite/btcec/privkey_test.go
• Dockerfile
• third_party/btcsuite/btcec/doc.go
• third_party/btcsuite/btcec/pubkey_test.go
• pkg/bitcoin/transaction.go
• third_party/btcsuite/btcec/gensecp256k1.go
• third_party/btcsuite/btcec/precompute.go
• third_party/btcsuite/btcec/VENDOR.md
• third_party/btcsuite/btcec/genprecomps.go
• pkg/bitcoin/estimator.go
• third_party/btcsuite/btcec/ciphering_test.go
• pkg/bitcoin/script.go
• third_party/btcsuite/btcec/example_test.go
• third_party/btcsuite/btcec/signature_test.go
• third_party/btcsuite/btcec/pubkey.go
• third_party/btcsuite/btcec/ciphering.go
• third_party/btcsuite/btcec/btcec.go
• third_party/btcsuite/btcec/btcec_test.go
• third_party/btcsuite/btcec/signature.go
• third_party/btcsuite/btcec/privkey.go
• go.mod
• third_party/btcsuite/btcec/field_test.go

[coderabbitai]

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Correct the documentation typos.

“suite of test,” “signficantly,” “developers original,” and “parsed form raw bytes” reduce clarity.

Proposed fix

- standard crypto/ecdsa packages provided with go.  A comprehensive suite of test
+ standard crypto/ecdsa packages provided with Go. A comprehensive suite of tests
  is provided to ensure proper functionality.  Package btcec was originally based
  on work from ThePiachu which is licensed under the same terms as Go, but it has
- signficantly diverged since then.  The btcsuite developers original is licensed
+ significantly diverged since then. The btcsuite developers' original is licensed
  under the liberal ISC license.
...
- parsed form raw bytes and serializing the generated signature.
+ parsed from raw bytes and serializing the generated signature.

Also applies to: 28-30

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@third_party/btcsuite/btcec/README.md` around lines 8 - 14, Correct the
documentation typos in the btcec README: change “suite of test” to “suite of
tests,” fix “signficantly” to “significantly,” revise “developers original” to
the grammatically correct possessive wording, and correct “parsed form raw
bytes” to “parsed from raw bytes” in the additional affected section.

Source: Linters/SAST tools

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@third_party/btcsuite/btcec/VENDOR.md`:
- Around line 53-54: Update the multiplication markers in the retention-ceiling
text of VENDOR.md so they do not trigger MD037; replace each `*` between numeric
operands with `×` or an escaped asterisk, preserving the displayed calculations.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: aa735ae6-3661-4fe2-9ffd-6b6417b97ddc

📥 Commits

Reviewing files that changed from the base of the PR and between 626538d and 69da1aa.

📒 Files selected for processing (7)

• pkg/bitcoin/electrum/transaction.go
• pkg/bitcoin/electrum/transaction_test.go
• pkg/bitcoin/transaction.go
• pkg/bitcoin/transaction_builder.go
• pkg/bitcoin/transaction_builder_test.go
• pkg/bitcoin/transaction_test.go
• third_party/btcsuite/btcec/VENDOR.md

🚧 Files skipped from review as they are similar to previous changes (2)

• pkg/bitcoin/transaction_builder.go
• pkg/bitcoin/transaction.go

[coderabbitai]

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Escape the multiplication markers.

The * characters trigger MD037 warnings; use × or escape them.

Proposed fix

- to 524 MB (125 * 4 MiB), about an 82x increase.
+ to 524 MB (125 × 4 MiB), about an 82x increase.

🧰 Tools

🪛 markdownlint-cli2 (0.23.1)

[warning] 53-53: Spaces inside emphasis markers

(MD037, no-space-in-emphasis)

---

[warning] 54-54: Spaces inside emphasis markers

(MD037, no-space-in-emphasis)

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@third_party/btcsuite/btcec/VENDOR.md` around lines 53 - 54, Update the
multiplication markers in the retention-ceiling text of VENDOR.md so they do not
trigger MD037; replace each `*` between numeric operands with `×` or an escaped
asterisk, preserving the displayed calculations.

Source: Linters/SAST tools