@companion-ai/feynman@0.5.43
The open source AI research agent.
AI Security Review
scanned 22d ago · by lpm-firewall-aiInspected source shows a version-only preinstall check, user-invoked project scaffolding, and disclosed package-aligned telemetry. These behaviors do not establish a concrete attack surface.
Decision evidence
public snapshot- The preinstall hook runs a Node version check, and that script exits only when the version is unsupported.
- The executable loads the built CLI when the user runs it.
- The project init command creates an AGENTS.md only when none exists; it is registered as an explicit command.
- The CLI initializes usage telemetry and shows a notice describing collected data, including error messages and stack traces.
- Telemetry defaults to the package's PostHog endpoint and supports an environment-variable opt-out.
Source & flagged code
6 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@0.5.43.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.43 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.