feat: add prompt-defense-audit + misp-mcp-server to Tools#183
Conversation
- prompt-defense-audit: regex-based prompt defense scanner (17+ vectors) - misp-mcp-server: MISP MCP server with built-in injection defense
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📜 Recent review details🔇 Additional comments (2)
WalkthroughREADME.md의 Tools 목록에 두 개의 새 항목( 변경 사항도구 목록 확장
개요README.md의 도구 섹션이 확장되어 두 개의 새로운 프로젝트 항목(prompt-defense-audit, misp-mcp-server)이 기존 도구 목록에 추가되었습니다. 변경 사항도구 목록 확장
예상 검토 노력🎯 1 (Trivial) | ⏱️ ~2분 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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.
Built for teams:
One agent for your entire SDLC. Right inside Slack. 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 |
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (2)
README.md (2)
117-117: 🏗️ Heavy lift도구 목록 정렬 고려 사항
Tools 섹션의 항목들이 알파벳 순서로 정렬되어 있지 않습니다. 새로운 도구들이 목록 중간과 끝에 삽입되어 일관된 순서가 없습니다.
장기적인 유지보수성 향상을 위해 전체 Tools 섹션을 알파벳 순으로 정렬하는 것을 고려해보세요. 이렇게 하면 향후 기여자들이 새 항목을 어디에 추가해야 할지 명확해집니다.
Also applies to: 123-123
🤖 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 117, The Tools list in README.md is not alphabetized (e.g., the "prompt-defense-audit" entry is out of order); please reorder all items in the Tools section into strict alphabetical order (case-insensitive) so new entries have a clear insertion point—update the list where "prompt-defense-audit" and other entries appear to follow A→Z and ensure any badge lines remain attached to their respective entries.
117-117: ⚡ Quick win설명 스타일 개선 제안
다음 두 가지 스타일 개선을 고려해주세요:
- "MISSING"을 대문자로 강조한 부분을 일반 소문자로 변경 ("missing defenses")
- "deps"를 전체 단어 "dependencies"로 변경
다른 도구 설명과의 일관성을 위해 표준 대소문자 사용과 약어 대신 전체 단어 사용을 권장합니다.
♻️ 제안된 개선안
-- [prompt-defense-audit](https://github.com/ppcvote/prompt-defense-audit): a deterministic prompt defense scanner that checks system prompts for MISSING defenses against 17+ prompt-injection vectors. Pure regex, <5ms, zero deps.  +- [prompt-defense-audit](https://github.com/ppcvote/prompt-defense-audit): a deterministic prompt defense scanner that checks system prompts for missing defenses against 17+ prompt-injection vectors. Pure regex, <5ms, zero dependencies. 🤖 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 117, Update the README description for the prompt-defense-audit entry: change the word "MISSING" to lowercase "missing defenses" and replace the abbreviation "deps" with the full word "dependencies" in the sentence describing the tool (the line containing "prompt-defense-audit" in the README).
🤖 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 `@README.md`:
- Around line 123-124: Remove the extraneous blank line immediately following
the "misp-mcp-server" list item in the Tools section so it matches the other
entries' spacing; locate the markdown list entry containing
"[misp-mcp-server](https://github.com/ppcvote/misp-mcp-server)" and delete the
blank line after it to maintain consistent list formatting.
---
Nitpick comments:
In `@README.md`:
- Line 117: The Tools list in README.md is not alphabetized (e.g., the
"prompt-defense-audit" entry is out of order); please reorder all items in the
Tools section into strict alphabetical order (case-insensitive) so new entries
have a clear insertion point—update the list where "prompt-defense-audit" and
other entries appear to follow A→Z and ensure any badge lines remain attached to
their respective entries.
- Line 117: Update the README description for the prompt-defense-audit entry:
change the word "MISSING" to lowercase "missing defenses" and replace the
abbreviation "deps" with the full word "dependencies" in the sentence describing
the tool (the line containing "prompt-defense-audit" in the README).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
- prompt-defense-audit: 'MISSING' → 'missing', 'deps' → 'dependencies' (lowercase + full word for consistency with other Tools descriptions) - Remove extraneous blank line between Agentic Radar and misp-mcp-server (the blank was breaking the list into two CommonMark <ul> blocks; kept the blank before ## Articles since that's the standard heading spacing) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds two open-source tools to the Tools section.
prompt-defense-audit
ppcvote/prompt-defense-audit — deterministic scanner that checks LLM system prompts for missing defenses against 17+ prompt-injection vectors (OWASP LLM01 mapping, plus 5 newer vectors covering tool-call hijacking and indirect injection). Pure regex, <5ms, zero deps, npm + CLI.
Differentiates from existing tools in this list:
misp-mcp-server
ppcvote/misp-mcp-server — Node MCP server for MISP (Malware Information Sharing Platform), with
prompt-defense-audit's output scanner baked in. Addresses a specific threat: adversarial seeding of threat-intel data designed to hijack downstream LLM agents (an under-discussed risk as SOC teams adopt Claude/Cursor for triage).Read-only by design. Tracks MISP/MISP#10745.
Both MIT licensed.
Thanks for maintaining this list 🙏
Summary by CodeRabbit