@companion-ai/feynman@0.3.12
Research-first CLI agent built on Pi and alphaXiv
AI Security Review
scanned 3mo ago · by lpm-firewall-aiThe package is not malicious by source evidence, but its automatic CLI-time setup and patching of a packaged AI-agent runtime warrants a warning under the lifecycle-risk policy.
Decision evidence
public snapshot- bin/feynman.js imports patch-embedded-pi before launching dist.
- Patch script restores and patches a bundled Pi runtime on CLI use.
- It writes under ~/.feynman and patches pi-subagents/pi-otel there.
- preinstall only validates the Node version; it has no file or network mutation.
- The bundled .tgz is a SHA-256-checked runtime dependency workspace.
- Research API calls and environment keys are tool-specific, user-invoked functionality; no harvesting path found.
- No covert exfiltration, remote payload execution, or foreign agent-config write was found.
Source & flagged code
14 flaggedPackage defines install-time lifecycle scripts.
package.jsonView on unpkgPackage source references a known benign dynamic code generation pattern.
dist/workbench-web/assets/3Dmol-D4OPhBxL.jsView on unpkg · L1692Findings
Affected versions and remediation
This report applies to @companion-ai/feynman@0.3.12.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.3.12 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.