pennyrouter@0.3.58
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 11d ago · by lpm-firewall-aiThe inspected source supports a warning for explicit user-command changes to agent configuration, but does not show unconsented install-time mutation or a concrete attack. Classify as suspicious capability risk rather than malicious behavior.
Decision evidence
public snapshot- The manifest exposes a command-line entry point and lists no npm lifecycle hooks.
- Launcher setup changes Claude Code's status line and persists the updated settings.
- The status-line setup preserves an existing user command by wrapping it.
- The explicit MCP registration command writes PennyRouter's server registration for supported agents.
- MCP registration is also offered during the install flow unless disabled.
- Inspected source shows agent configuration changes within PennyRouter's launcher and MCP setup paths; it does not establish an install-time attack or credential theft.
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@0.3.58.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.58 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.