pennyrouter@0.3.49
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe source shows a first-party, user-invoked agent integration that changes Claude Code statusline configuration. Under the agent integration policy this guarded capability merits a warning; the inspected code does not establish malicious activity.
Decision evidence
public snapshot- The manifest exposes a user-run CLI and has no install lifecycle hook.
- The CLI launch setup configures and persists a Claude Code statusline command; the integration preserves an existing command for later restoration.
- The other indicated locations concern per-profile Codex config, test fixtures, session paths, or local transcript state; these excerpts do not establish a separate attack.
- This is a guarded agent configuration capability activated through setup, with no confirmed attack behavior.
- The package describes itself as an installer and manager for local coding-agent integrations.
Source & flagged code
7 flagged · loading sourceSource writes installer persistence such as shell profile or service configuration.
src/launch.test.jsView on unpkg · L1Findings
Affected versions and remediation
This report applies to pennyrouter@0.3.49.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.49 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.