pennyrouter@0.3.2
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe package has a guarded, user-invoked agent integration setup capability, so a warning is appropriate. The inspected source does not support a malware or publish-block finding.
Decision evidence
public snapshot- The manifest exposes a CLI binary and no npm install lifecycle hook.
- The explicit CLI install path selects harnesses and installs integrations; Claude Code statusline setup replaces its statusLine command with a package script while retaining an existing command for wrapping.
- The CLI also registers a PennyRouter MCP server in Claude Code or Codex configuration, and its entry launches this package's MCP command.
- The inspected integration changes are initiated by the CLI install command; no automatic npm install hook was found.
- The statusline code reads PennyRouter settings and its existing command, consistent with a package-owned integration rather than a foreign control-surface takeover.
Source & flagged code
6 flagged · loading sourceSource writes installer persistence such as shell profile or service configuration.
src/launch.test.jsView on unpkg · L28Source gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.
Findings
Affected versions and remediation
This report applies to pennyrouter@0.3.2.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.2 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.