com.arcself/arc-security

MCPcommunity
v0.5.1com.arcselfUnknownUpdated 4mo agonpmGitHub

Scan AI agent skills for 25 attack classes + runtime monitoring. 1,316+ findings.

AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped. Add to your MCP client (Claude Code, Cursor, VS Code, etc.): That's it. One command install, two-line config. Ask your AI assistant: "Is the…

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
4mo agoLast update
Package
Authorcom.arcself
LicenseUnknown
Version0.5.1
Sourcemcp-registry
npmarc-security-mcp
GitHubArcSelf/arc-security-mcp
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/25
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/10
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
—npm provenance (Sigstore)+0/5
→ Publish from GitHub Actions with the --provenance flag
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 0 resolved · none vulnerable
Tool surface—
Security scan✓ Cleanv0.5.1 · 20d ago
EvalsNone
IndexedJun 13, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.

About

AI agent security: scan skills for 25 attack classes + runtime monitoring (EDR for AI agents). Real-time scanning, behavioral anomaly detection, session monitoring, exfiltration alerts. 1,316+ findings from 450+ audits. OWASP Agentic AI Top 10 mapped. Add to your MCP client (Claude Code, Cursor, VS Code, etc.): That's it. One command install, two-line config. Ask your AI assistant: "Is the kubectl skill safe?" "Scan the hello-world skill for security issues" (fetches from ClawHub in real-time)…

Keywords
mcp