pennyrouter@0.3.38
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe package has no npm lifecycle hook, but its CLI can configure a first-party MCP integration and Claude statusline for agent use. This is a guarded agent integration capability, not evidence of a confirmed attack, so a warning is appropriate.
Decision evidence
public snapshot- package.json exposes a CLI entrypoint and declares no npm lifecycle hook.
- The install flow registers an MCP server after routing setup when MCP registration is enabled and dry-run is off.
- The managed MCP entry launches PennyRouter's own MCP command and passes harness and optional gateway settings.
- Claude launch setup writes a managed statusline script and updates the launch settings.
- The integration writes are tied to explicit CLI install or launch flows; no automatic npm install hook was found.
- The MCP entry is package-owned and namespaced, and registration code preserves or rejects conflicting user entries.
Source & flagged code
10 flagged · loading sourcePackage source references child process execution.
standalone/web-demo/server.mjsView on unpkg · L3A single source file combines environment access, network access, and code or shell execution; review context before blocking.
standalone/web-demo/server.mjsView on unpkg · L273Findings
Affected versions and remediation
This report applies to pennyrouter@0.3.38.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.38 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.