pennyrouter@0.3.17
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe manifest exposes a command-line tool without install hooks. Inspected network and agent configuration behavior is consistent with user-invoked setup and gateway integration, so the scanner hints do not establish malicious behavior.
Decision evidence
public snapshot- package.json exposes a command-line entry point and has no install lifecycle hook.
- Claude statusline setup is reached through launcher code and preserves the existing statusline setting.
- The statusline sends a key to the configured gateway for status data; no unrelated recipient is established.
- MCP registration adds a PennyRouter-owned entry and preserves existing entries.
- The flagged session and thread-session locations concern harness session paths; the CodeGPT install plan avoids editing IDE settings.
- Upstream credentials are deliberately submitted to the selected gateway during setup.
Source & flagged code
6 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@0.3.17.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.17 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.