Skip to content

Add ClawGuard Shield — multi-language AI agent security scanner with EU AI Act mapping#1

Open
joergmichno wants to merge 1 commit intocode-agents:mainfrom
joergmichno:add-clawguard-shield
Open

Add ClawGuard Shield — multi-language AI agent security scanner with EU AI Act mapping#1
joergmichno wants to merge 1 commit intocode-agents:mainfrom
joergmichno:add-clawguard-shield

Conversation

@joergmichno
Copy link
Copy Markdown

Summary

Adds ClawGuard Shield to the MCP Security Tools page and comparison table.

What ClawGuard Shield does:

  • Detects prompt injection, tool poisoning, data exfiltration, SSRF, jailbreaks across 189 patterns in 15 languages
  • Zero LLM dependency — pure regex-based, <10ms scan time
  • EU AI Act compliance mapping — unique feature not offered by other tools in the comparison
  • OWASP LLM Top 10 + Agentic Top 10: 100% coverage
  • F1 Score: 97.4% on benchmark suite
  • Available as Python library, npm package, MCP server, and REST API
  • MIT licensed

Links:

Adds ClawGuard Shield to the security tools listing and comparison table.

- 189 detection patterns across 15 languages
- Zero LLM dependency, regex-based, <10ms scan time
- EU AI Act compliance mapping (unique feature)
- OWASP LLM Top 10 + Agentic Top 10: 100% coverage
- F1 Score: 97.4%
- Available as Python, npm, MCP server, and REST API
- MIT licensed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant