crysk-loop
Warn
Audited by Socket on Oct 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill’s review-and-triage capabilities generally fit its purpose, and the listed GitHub data flows are coherent. Risk is elevated by unpinned execution of a package whose provenance is unverified, unspecified transitive skill installation, and autonomous pushes and PR comments without per-action approval. The evidence does not establish credential theft or malicious intent.
Confidence: 88%Severity: 72%
Audit Metadata