@companion-ai/feynman@0.5.20
Research-first CLI agent built on Pi and alphaXiv
AI Security Review
scanned 26d ago · by lpm-firewall-aiSource inspection shows a version-check-only preinstall hook, a launcher that loads the CLI, and an explicitly invoked project initialization command that preserves existing files. The scanner signals do not establish malicious behavior.
Decision evidence
public snapshot- The preinstall hook only runs a Node version check; no install-time policy or agent configuration mutation is shown.
- The flagged project behavior is registered as an explicit `init` command and targets project-local research files.
- The launcher loads the CLI entrypoint after checking that its Pi peer dependencies resolve.
- The inspected CLI excerpt shows a child process for the bundled alpha command, without evidence of a hidden payload or credential transfer.
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@0.5.20.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.20 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.