op55-compose
Warn
Audited by Socket on Nov 2, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s stated purpose is coherent with writing cue and score files, and there is no visible credential theft or external exfiltration. However, its real execution depends on unverified sibling tooling and transitive local skills, so install/execution trust is not fully auditable from the provided content.
Confidence: 85%Severity: 72%
Audit Metadata