@companion-ai/feynman@0.5.13
Research-first CLI agent built on Pi and alphaXiv
AI Security Review
scanned 26d ago · by lpm-firewall-aiSource inspection found no concrete malicious behavior. The lifecycle hook is a version check, and the flagged project configuration writes occur only through an explicit command that preserves existing files.
Decision evidence
public snapshot- The preinstall hook only runs a Node version check; it exits when the installed Node version is too old.
- The project init command is user-invoked and targets the current project directory; it creates AGENTS.md only if it does not already exist.
- The CLI entrypoint checks the Node version before importing the bundled CLI.
- The bundled CLI loads a .env file from the working directory when present.
- Hugging Face credentials are attached to requests made by the research tool to its Hugging Face API.
- Telemetry disclosure describes usage and error data and states that prompts, model output, paper content, and tool arguments are not sent.
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@0.5.13.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.13 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.