@companion-ai/feynman@0.5.36
The open source AI research agent.
AI Security Review
scanned 24d ago · by lpm-firewall-aiSource inspection shows a version-check-only preinstall hook and a user-invoked init command that preserves an existing AGENTS.md. The inspected CLI code does not establish the scanner’s suspected attack behavior, so the package is clean.
Decision evidence
public snapshot- The preinstall hook only runs a Node.js version check and exits when the version is unsupported.
- The init command is explicitly registered as a user-invoked Pi command; it creates project notes and writes AGENTS.md only when that file is absent.
- The package CLI resolves its bundled alpha CLI and starts it as a child process for that feature.
Source & flagged code
6 flaggedPackage defines install-time lifecycle scripts.
package.jsonView on unpkgSource gates dangerous network, credential, or execution behavior behind CI, host, platform, time, or geo fingerprint checks.
bin/feynman.jsView on unpkg · L23Findings
Affected versions and remediation
This report applies to @companion-ai/feynman@0.5.36.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.36 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.