pennyrouter@0.3.64
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe manifest exposes a CLI without install lifecycle hooks, while the explicit harness setup modifies Claude agent configuration and installs a package-owned statusline command. That capability merits a warning; the inspected source does not establish a concrete attack.
Decision evidence
public snapshot- The manifest exposes a CLI and has no install, preinstall, or postinstall hook.
- The Codex test writes fixture configuration and authentication data under a temporary test root.
- The flagged launch location derives a PennyRouter Codex config path from CODEX_HOME or the user’s .codex directory.
- The launch test creates Claude and Codex directories for its fixture.
- The MCP registration test creates Codex configuration for a status check.
- The pilots test creates Claude settings and a fixture file to test permission handling.
- The statusline reads Claude settings and obtains its PennyRouter key from settings or process environment.
- The Codex session path helper identifies where session files are stored.
- The configured statusline can run a saved user command through a shell, as part of wrapping that user’s existing statusline.
- The package contains network and environment-variable use; the inspected evidence does not establish a malicious recipient or credential theft.
Source & flagged code
7 flagged · loading sourceThis package version adds a dangerous source file absent from the previous stored version; route for source-aware review.
src/launch.test.jsView on unpkgSource 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@0.3.64.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.64 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.