pennyrouter@0.3.37
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe manifest declares no npm lifecycle hook, and the inspected integration paths are consistent with a user-invoked CLI installer and local session handling. Scanner signals alone do not establish malicious behavior.
Decision evidence
public snapshot- package.json exposes a CLI and lists only start and check scripts; no install lifecycle hook is declared.
- src/cli.js dispatches the install behavior only when the user invokes the install command.
- src/statusline.js reads Claude Code settings as part of its statusline integration; src/launch.js selects a PennyRouter-specific Codex profile file.
- The thread-session modules and web demo access local agent session directories; the inspected excerpts show no attack behavior.
- The remaining required source locations contain local path handling, test setup, or MCP integration context, with no confirmed attack surface.
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 · L216Findings
Affected versions and remediation
This report applies to pennyrouter@0.3.37.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.37 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.