io.github.AgentSafe-AI/tooltrust-scanner

MCPcommunity
v1.0.9io.github.AgentSafe-AIUnknownUpdated 3mo agonpmGitHub

Scans MCP servers for prompt injection, data exfiltration, and privilege escalation.

Scan MCP servers for prompt injection, data exfiltration, risky permissions, supply-chain threats, and privilege escalation before your agent blindly trusts them. First run downloads a ~10MB Go binary from GitHub Releases and caches it at . Subsequent runs use the cached binary with no download. Prompt injection and tool poisoning hidden in descriptions Excessive permissions such as , , , and…

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
3mo agoLast update
Package
Authorio.github.AgentSafe-AI
LicenseUnknown
Version1.0.9
Sourcemcp-registry
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
Dependencies0 resolved · none vulnerable
Tool surface
Security scan✓ Cleanv1.1.9 · 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

Scan MCP servers for prompt injection, data exfiltration, risky permissions, supply-chain threats, and privilege escalation before your agent blindly trusts them. First run downloads a ~10MB Go binary from GitHub Releases and caches it at . Subsequent runs use the cached binary with no download. Prompt injection and tool poisoning hidden in descriptions Excessive permissions such as , , , and Supply-chain CVEs and known compromised package versions Suspicious npm lifecycle scripts that execute…

Keywords
mcp