@companion-ai/feynman@0.5.19
Research-first CLI agent built on Pi and alphaXiv
AI Security Review
scanned 26d ago · by lpm-firewall-aiInspected source shows a version-check preinstall hook and research tools that send optional Hugging Face credentials to Hugging Face endpoints. The scanner signals do not establish malicious behavior, so this package is clean.
Decision evidence
public snapshot- package.json limits its preinstall hook to a Node.js version check.
- The project initialization command writes project-local research folders and creates AGENTS.md only when absent.
- The launcher checks the Pi peer runtime and loads the bundled CLI.
- The bundled alpha command passes arguments to a package-resolved child process and inherits the environment.
- Hugging Face tools read HF tokens and send them with requests to Hugging Face URLs.
Source & flagged code
5 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@0.5.19.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.19 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.