@companion-ai/feynman@0.5.53
The open source AI research agent.
AI Security Review
scanned 13d ago · by lpm-firewall-aiSource inspection found a version-check install hook, user-invoked project setup that preserves an existing AGENTS.md, and alphaXiv authentication directed to its intended service. The scanner signals do not establish malicious behavior.
Decision evidence
public snapshot- The install hook only runs a Node version check; the launcher checks the runtime version before loading the CLI.
- The project setup command creates research session folders and writes AGENTS.md only when it is absent.
- The alphaXiv library exposes authentication helpers, and its auth flow targets alphaXiv’s authentication service; the CLI calls login from its alpha login command.
- The inspected dependencies provide prompt, alphaXiv research, and XML parsing functionality.
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@0.5.53.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.53 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.