@companion-ai/feynman@0.5.38
The open source AI research agent.
AI Security Review
scanned 24d ago · by lpm-firewall-aiThe preinstall hook only checks the Node version, and the inspected agent-related writes are bounded to project scaffolding invoked by the init command. The static hints did not establish malicious behavior.
Decision evidence
public snapshot- package.json's preinstall only runs a Node version check.
- bin/feynman.js resolves the Pi runtime as peer dependencies, then loads the package CLI.
- The project init command targets AGENTS.md and notes/session-logs under the active project directory.
- dist/cli.js initializes Feynman's own home and agent directory during CLI startup; the inspected source shows no confirmed attack behavior.
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@0.5.38.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.38 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.