@companion-ai/feynman@0.5.14
Research-first CLI agent built on Pi and alphaXiv
AI Security Review
scanned 26d ago · by lpm-firewall-aiThe flagged preinstall hook only checks the Node version, while `/init` is an explicit command that can write project agent context. This warrants a warning for agent-configuration capability, but the inspected source does not establish malicious behavior.
Decision evidence
public snapshot- The install hook only runs a Node version check.
- The registered `/init` command can create a project-root `AGENTS.md` and session-log folders when invoked.
- The generated guide is a Feynman project template; the write is not triggered by npm installation.
- The inspected sources show no concrete malicious behavior or confirmed attack surface.
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@0.5.14.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.14 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.