docs: add OWASP Agent Memory Guard to security docs - #8167
Open
MOHAMMED WASIM KHAN (wasim-builds) wants to merge 4 commits into
Open
docs: add OWASP Agent Memory Guard to security docs#8167MOHAMMED WASIM KHAN (wasim-builds) wants to merge 4 commits into
MOHAMMED WASIM KHAN (wasim-builds) wants to merge 4 commits into
Conversation
added 2 commits
September 2, 2026 11:23
Added documentation for path traversal protection, security best practices, and indirect prompt injection mitigation. Fixes microsoft#7181
Added section describing ASI06 memory poisoning risk and the OWASP Agent Memory Guard reference implementation, including installation instructions and key features. Fixes microsoft#7683
added 2 commits
September 4, 2026 09:03
Added encoding="utf-8" to all file open calls in redirects.py so the script behaves consistently on Windows and any locale where the default system encoding is not UTF-8. Fixes microsoft#7749
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Added a section to the Magentic-One documentation covering the OWASP Agent Memory Guard, addressing ASI06 (Memory Poisoning) from the OWASP Top 10 for Agentic Applications.
Why
Persistent memory is a powerful feature, but it also introduces attack surface. If an agent's memory gets poisoned — through indirect prompt injection, corrupted tool output, or adversarial user input — that malicious content can influence every future session. The OWASP Agent Memory Guard gives users a concrete, low-overhead way to add integrity checks and policy enforcement around memory reads and writes.
Changes
Downloading agent_memory_guard-0.3.1-py3-none-any.whl.metadata (17 kB)
Collecting PyYAML>=6.0 (from agent-memory-guard)
Downloading pyyaml-6.0.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl.metadata (2.4 kB)
Downloading agent_memory_guard-0.3.1-py3-none-any.whl (82 kB)
Downloading pyyaml-6.0.3-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl (801 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 801.6/801.6 kB 1.9 MB/s 0:00:00
Installing collected packages: PyYAML, agent-memory-guard
Successfully installed PyYAML-6.0.3 agent-memory-guard-0.3.1) and a note on adoption (UK Government BEIS Inspect AI)
Testing
Documentation-only change. No code changes, no tests required.
Fixes #7683