agentic-loop
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires running the remote npm package "@mhrj/mcp-agent-loop" via npx (see "command": "npx", "args": ["-y", "@mhrj/mcp-agent-loop"]), which fetches and executes remote code at runtime and therefore can directly control agent behavior.
Issues (1)
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata