@companion-ai/feynman@0.5.39
The open source AI research agent.
AI Security Review
scanned 23d ago · by lpm-firewall-aiThe inspected lifecycle hook only checks the Node version, and the flagged project and account features have bounded, user-facing behavior. The runtime telemetry is disclosed and sent to the package's configured PostHog service; the reviewed evidence does not establish malicious behavior.
Decision evidence
public snapshot- The preinstall hook runs a Node version check and exits on unsupported versions.
- The launcher loads the bundled CLI as its normal entrypoint.
- The project init command creates AGENTS.md and a session log README only when they do not already exist.
- AlphaXiv account tools require a signed-in session and perform requested paper searches.
- The CLI sends disclosed usage telemetry to its configured PostHog service; the inspected code collects command metadata.
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@0.5.39.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.39 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.