shelf
Warn
Audited by Socket on Sep 10, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
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