Add OWASP Agent Memory Guard – AI agent memory security framework

[vgudur-dev]

What is this?

OWASP Agent Memory Guard is an official OWASP incubator project providing a security framework for protecting AI agent memory from poisoning, injection, and exfiltration attacks.

Why add it?

• Official OWASP project — directly relevant to LLM/AI security
• Addresses the growing attack surface of AI agent long-term memory (vector stores, episodic memory, session context)
• Provides practical drop-in middleware for LangChain, LlamaIndex, and custom pipelines
• Includes detection hooks, sanitization, and audit logging
• Aligns with OWASP Top 10 for LLM Applications (A03: Training Data Poisoning, A07: Insecure Plugin Design)

Added entry

- [OWASP Agent Memory Guard](https://github.com/OWASP/www-project-agent-memory-guard) – An official OWASP security framework for protecting AI agent memory from poisoning, injection, and exfiltration attacks. Provides detection middleware, sanitization hooks, and audit logging for LangChain, LlamaIndex, and custom agent pipelines.

Summary by CodeRabbit

문서

• README의 도구(Tools) 섹션에 OWASP Agent Memory Guard를 추가했습니다. AI 에이전트 메모리를 중독, 주입, 유출로부터 보호하는 보안 프레임워크로, 탐지 미들웨어, 살균 후크, 감사 로깅을 포함합니다.

[coderabbitai]

요약

README 파일의 Tools 섹션에 OWASP Agent Memory Guard라는 새로운 보안 도구 항목을 추가했습니다.

변경 사항

도구 문서화 추가

레이어 / 파일(s)	요약
문서화 업데이트 README.md	Tools 섹션에 OWASP Agent Memory Guard 항목이 추가되었습니다. 이는 AI 에이전트 메모리를 중독, 주입 및 유출로부터 보호하는 OWASP 보안 프레임워크를 설명합니다.

예상 코드 리뷰 난이도

🎯 1 (Trivial) | ⏱️ ~1 분

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and specifically describes the main change: adding a new OWASP Agent Memory Guard entry to the README, which matches the actual modification in the pull request.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
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.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

Tip

💬 Introducing Slack Agent: The best way for teams to turn conversations into code.

Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.

• Generate code and open pull requests
• Plan features and break down work
• Investigate incidents and troubleshoot customer tickets together
• Automate recurring tasks and respond to alerts with triggers
• Summarize progress and report instantly

Built for teams:

• Shared memory across your entire org—no repeating context
• Per-thread sandboxes to safely plan and execute work
• Governance built-in—scoped access, auditability, and budget controls

One agent for your entire SDLC. Right inside Slack.

👉 Get started

---

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 and usage tips.}

[coderabbitai]

🧹 Nitpick comments (1)

README.md (1)

107-107: ⚡ Quick win

일관성을 위해 GitHub 스타 배지 추가를 고려하세요.

Tools 섹션의 다른 대부분의 항목들(12개 중 10개)이 GitHub 스타 배지를 포함하고 있습니다. 시각적 일관성과 프로젝트 인기도 표시를 위해 동일한 형식을 따르는 것이 좋습니다.

🎨 GitHub 스타 배지를 추가하는 제안

-- [OWASP Agent Memory Guard](https://github.com/OWASP/www-project-agent-memory-guard) – An official OWASP security framework for protecting AI agent memory from poisoning, injection, and exfiltration attacks. Provides detection middleware, sanitization hooks, and audit logging for LangChain, LlamaIndex, and custom agent pipelines.
+- [OWASP Agent Memory Guard](https://github.com/OWASP/www-project-agent-memory-guard): An official OWASP security framework for protecting AI agent memory from poisoning, injection, and exfiltration attacks. Provides detection middleware, sanitization hooks, and audit logging for LangChain, LlamaIndex, and custom agent pipelines. ![GitHub Repo stars](https://img.shields.io/github/stars/OWASP/www-project-agent-memory-guard?style=social)

참고: en-dash(–)를 colon(:)으로 변경하여 다른 항목들과의 구두점 일관성도 개선했습니다.

🤖 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 `@README.md` at line 107, Update the "OWASP Agent Memory Guard" list item to
match the other Tools entries by adding a GitHub star badge next to the link and
replace the en-dash with a colon for punctuation consistency; locate the list
entry containing the text "OWASP Agent Memory Guard" and insert the standard
GitHub stars badge markdown (e.g., a shields.io or GitHub badge) after the link
and change "–" to ":" so the item matches the format used by the other tools.

🤖 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.

Nitpick comments:
In `@README.md`:
- Line 107: Update the "OWASP Agent Memory Guard" list item to match the other
Tools entries by adding a GitHub star badge next to the link and replace the
en-dash with a colon for punctuation consistency; locate the list entry
containing the text "OWASP Agent Memory Guard" and insert the standard GitHub
stars badge markdown (e.g., a shields.io or GitHub badge) after the link and
change "–" to ":" so the item matches the format used by the other tools.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: e5ff8752-dee5-4293-8819-71091a5c855a

📥 Commits

Reviewing files that changed from the base of the PR and between c8ae124 and 3e73b5b.

📒 Files selected for processing (1)

• README.md

📜 Review details

🔇 Additional comments (1)

README.md (1)

107-107: 검증 완료 — 추가 조치 필요 없음

제공된 저장소는 OWASP 공식 Incubator 프로젝트로 확인되었으며, 설명된 모든 기능(LangChain/LlamaIndex 지원, 감지 미들웨어, 감사 로깅, 위협 탐지 등)이 정확합니다.