shelf

Warn

Audited by Socket on Sep 10, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: The skill’s stated purpose and local file/storage behavior are coherent and proportionate, and there is no sign of credential theft, remote exfiltration, or dangerous command injection. However, it requires executing a bundled `helix` binary whose provenance is not verifiable from the provided evidence, which creates a mandatory high supply-chain risk for an AI agent skill.

Confidence: 89%Severity: 72%
Audit Metadata
Analyzed At
Sep 10, 2026, 05:20 PM
Package URL
pkg:socket/skills-sh/teamhelix-ai%2Fhelix%2Fshelf%2F@af1463e3c5059ac3ed296d12994bd90922a37a630002bce2ec24fb85a86144cc
Security Audit — socket — shelf