pennyrouter@0.3.69
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 6d ago · by lpm-firewall-aiSource inspection found no npm install hook or concrete malicious behavior. The reviewed network and configuration activity is tied to user-run PennyRouter setup and its gateway integration.
Decision evidence
public snapshot- The manifest exposes a CLI and lists start and check scripts; the binary delegates to the CLI. No npm install lifecycle hook is declared.
- CLI setup creates an authorization session with an operating-system label and selected harness names, using PennyRouter’s app URL by default. The hostname is sent as a key label only in the explicit private-gateway flow.
- Claude sign-in reads a local OAuth token and sends it to the configured gateway only when account linking is enabled and the account is not already linked; the CLI invokes this during Claude Code setup.
- The required agent-related locations concern local configuration paths, session data, and test fixtures. The launcher configures the Claude status line while preserving an existing user command.
- CodeGPT setup prints manual instructions, and the standalone demo server binds to loopback.
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@0.3.69.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.69 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.