@companion-ai/feynman@0.3.47
Research-first CLI agent built on Pi and alphaXiv
AI Security Review
scanned 2mo ago · by lpm-firewall-aiThe scanner findings are explained by a vendored runtime archive and a research-agent CLI. Direct inspection found a benign preinstall check and user-invoked setup, not a concrete malicious chain.
Decision evidence
public snapshot- Installation runs a local Node version check.
- The command launcher dynamically imports bundled runtime code and applies Pi runtime patches when the user runs the CLI.
- The package includes a compressed vendored runtime workspace.
- The preinstall source only checks the running Node version and prints guidance.
- No install-time download, shell execution, credential collection, or foreign agent configuration write was found.
- The skill installer downloads and writes files only when explicitly run by the user.
Source & flagged code
13 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 · L25Findings
Affected versions and remediation
This report applies to @companion-ai/feynman@0.3.47.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.3.47 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.