pennyrouter@0.3.6
Install and manage PennyRouter local coding-agent integrations.
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThis is an explicit-user-command agent integration with a meaningful unpinned future-release execution path. Static inspection found no lifecycle hook, hidden credential harvesting, or automatic malicious execution.
Decision evidence
public snapshot- The user-invoked installer registers an unpinned npx command in Claude Code and Codex MCP configuration, allowing a later agent start to fetch and run a future package release.
- The installer replaces Claude Code's status-line command with a generated script and records any existing command for later execution.
- The runtime installer appends a PennyRouter PATH block to shell startup files.
- package.json has no preinstall, install, or postinstall lifecycle hook.
- The configuration changes are reachable through explicit CLI install commands, not package installation.
- MCP registration backs up existing configuration and refuses to overwrite an unmanaged server with the same name.
- The inspected CodeGPT harness only offers manual setup and clipboard copying; it does not write IDE settings.
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@0.3.6.
See all versions of pennyrouter for other recorded verdicts.
- Review the evidence and your use of pennyrouter@0.3.6 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.