quality-gate
Warn
Audited by Socket on May 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s behavior is mostly coherent and tightly scoped for read-only quality verification, with no visible exfiltration, credential harvesting, or mutation paths. The main concern is reliance on an unverifiable local knowledge-gate CLI; under the required scoring rules, that unresolved binary provenance keeps overall risk high despite otherwise proportionate capabilities.
Confidence: 85%Severity: 72%
Audit Metadata