@companion-ai/feynman@0.5.57
The open source AI research agent.
AI Security Review
scanned 12d ago · by lpm-firewall-aiStatic inspection found no malicious install hook or credential theft. The default-on telemetry path can transmit failed tool-result text, creating a conditional privacy risk that supports a warning rather than a block.
Decision evidence
public snapshot- The preinstall hook runs a Node version check that exits on unsupported versions.
- The explicit init command creates AGENTS.md only when that file is absent.
- CLI startup initializes telemetry and passes its settings to the Pi child; the first-run notice describes error telemetry generally.
- Telemetry can be disabled through environment settings, and its default collector is Feynman's PostHog host.
- When a Pi tool reports an error, the extension extracts text from its result and includes it in a telemetry event sent to the configured collector.
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@0.5.57.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.57 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.