@companion-ai/feynman@0.5.51
The open source AI research agent.
AI Security Review
scanned 17d ago · by lpm-firewall-aiSource inspection found a version-only preinstall check and project writes guarded by the explicit `init` command. The CLI also has disclosed, configurable usage telemetry; no malicious behavior was established.
Decision evidence
public snapshot- The preinstall hook only runs a Node version check.
- The project file writes are in the explicitly registered `init` command and preserve existing files.
- The CLI launcher loads the bundled CLI after checking for its Pi peer dependencies.
- CLI telemetry is disclosed, sends usage and error data to the configured PostHog host, and can be disabled with environment settings.
- The inspected sources establish no malicious attack behavior.
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@0.5.51.
See all versions of @companion-ai/feynman for other recorded verdicts.
- Review the evidence and your use of @companion-ai/feynman@0.5.51 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.