feat(ai-red-teaming): wire agentic-probes 2026 attacks into generate_attack - #147
Open
rdheekonda wants to merge 1 commit into
Open
rdheekonda wants to merge 1 commit into
rdheekonda wants to merge 1 commit into
Conversation
…attack Register the new SDK primitives so the agent can select them: - transforms: yolo_mode_overwrite, arg_flag_injection, metachar_escape, deser_payload, trusted_proxy_char_exfil, tool_arg_covert_channel, line_jump_injection, optimized_rag_poison - scorers: rce_evidence_gate, approval_bypassed, trusted_proxy_exfil_detected, covert_channel_capacity, minja_activation_detected, line_jump_fired, poison_retrieved_and_steered - attack loop: iterinject_attack (short alias "iterinject") Catalogs and agent guide updated to match. Requires the SDK release that ships these modules.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Registers the new agentic-probes 2026 SDK primitives so the ai-red-teaming agent can select them via
generate_attack. Paired SDK PR: dreadnode/dreadnode-tiger#2522._TRANSFORM_DEFS:yolo_mode_overwrite,arg_flag_injection,metachar_escape,deser_payload,trusted_proxy_char_exfil,tool_arg_covert_channel,line_jump_injection,optimized_rag_poisonSCORER_REGISTRY(evidence-gated):rce_evidence_gate,approval_bypassed,trusted_proxy_exfil_detected,covert_channel_capacity,minja_activation_detected,line_jump_fired,poison_retrieved_and_steered_ATTACK_DEFS:iterinject_attack(short aliasiterinject)Dependency
Requires the SDK release that ships these modules (
dreadnode.transforms.tool_misuse_rce,.exfil_advanced,.mcp_lifecycle,.rag_optimization;dreadnode.scorers.*;dreadnode.airt.iterinject). Generated scripts import these by name, so this should merge after the SDK release lands.Validation
uv run pytest tests/test_attack_runner.py tests/test_tool_surface.py: 158 passed, 1 failed. The single failure (TestGenerateMultimodalAttack::test_generates_compiling_script_with_image) also fails on cleanorigin/main(local SDK version skew), so it is pre-existing and unrelated to this change.Test plan
generate_attackafter SDK release + deploy