Open
Conversation
Agent Guard is an open-source runtime governance firewall for AI agents covering 10/10 OWASP Agentic Top 10 risks. Features include policy enforcement, MCP security scanning, zero-trust Ed25519 identity, execution sandboxing, and kill switch. https: //github.com/Aveerayy/agent-guard Made-with: Cursor
개요README.md 파일의 "Tools" 섹션에 Agent Guard 도구에 대한 새로운 항목을 추가했습니다. GitHub 저장소 링크, 뱃지, 그리고 런타임 거버넌스 및 방화벽 기능에 대한 설명이 포함되었습니다. 변경 사항
예상 코드 리뷰 노력🎯 1 (Trivial) | ⏱️ ~2 minutes 🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment Warning |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@README.md`:
- Line 121: Replace the assertive claim "Covers 10/10 OWASP Agentic Top 10" in
the README line that follows the "[Agent Guard]" badge with a neutral phrasing
or add a reference link to supporting mapping; specifically update the phrase
"Covers 10/10 OWASP Agentic Top 10" to something like "Provides
mappings/mitigations for the OWASP Agentic Top 10" or "Aims to address OWASP
Agentic Top 10 (see mapping)" and, if available, append a link to the specific
mapping or evidence document so readers can verify the coverage.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
| - [WhistleBlower](https://github.com/Repello-AI/whistleblower): open-source tool designed to infer the system prompt of an AI agent based on its generated text outputs.  | ||
| - [Open-Prompt-Injection](https://github.com/liu00222/Open-Prompt-Injection): open-source tool to evaluate prompt injection attacks and defenses on benchmark datasets.  | ||
| - [Agentic Radar](https://github.com/splx-ai/agentic-radar): Open-source CLI security scanner for agentic workflows.  | ||
| - [Agent Guard](https://github.com/Aveerayy/agent-guard): Runtime governance firewall for AI agents — policy enforcement, MCP security scanning, zero-trust identity, execution sandboxing, and kill switch. Covers 10/10 OWASP Agentic Top 10.  |
There was a problem hiding this comment.
절대적 보안 커버리지 주장(“10/10”)은 근거 링크와 함께 완화해 주세요.
Line 121의 Covers 10/10 OWASP Agentic Top 10는 근거 문서 없이 단정적으로 보일 수 있습니다. 이 저장소 성격상 과장 표현 대신 “OWASP Agentic Top 10 대응 목표/매핑 제공”처럼 중립 문구로 바꾸거나, 해당 매핑 문서 링크를 같이 붙이는 편이 안전합니다.
✏️ 제안 diff
-- [Agent Guard](https://github.com/Aveerayy/agent-guard): Runtime governance firewall for AI agents — policy enforcement, MCP security scanning, zero-trust identity, execution sandboxing, and kill switch. Covers 10/10 OWASP Agentic Top 10. 
+- [Agent Guard](https://github.com/Aveerayy/agent-guard): Runtime governance firewall for AI agents — policy enforcement, MCP security scanning, zero-trust identity, execution sandboxing, and kill switch. Includes OWASP Agentic Top 10 mapping in project docs. 📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| - [Agent Guard](https://github.com/Aveerayy/agent-guard): Runtime governance firewall for AI agents — policy enforcement, MCP security scanning, zero-trust identity, execution sandboxing, and kill switch. Covers 10/10 OWASP Agentic Top 10.  | |
| - [Agent Guard](https://github.com/Aveerayy/agent-guard): Runtime governance firewall for AI agents — policy enforcement, MCP security scanning, zero-trust identity, execution sandboxing, and kill switch. Includes OWASP Agentic Top 10 mapping in project docs.  |
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@README.md` at line 121, Replace the assertive claim "Covers 10/10 OWASP
Agentic Top 10" in the README line that follows the "[Agent Guard]" badge with a
neutral phrasing or add a reference link to supporting mapping; specifically
update the phrase "Covers 10/10 OWASP Agentic Top 10" to something like
"Provides mappings/mitigations for the OWASP Agentic Top 10" or "Aims to address
OWASP Agentic Top 10 (see mapping)" and, if available, append a link to the
specific mapping or evidence document so readers can verify the coverage.
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.
What is Agent Guard?
Agent Guard is an open-source runtime governance firewall for AI agents. It sits between your agent framework and the tools agents call, policy-checking every action before it executes.
Why it fits this list
Single
pip install, MIT licensed, 114 tests, works with LangChain, OpenAI Agents, CrewAI, and AutoGen.Made with Cursor
Summary by CodeRabbit
릴리스 노트