conversation-lab
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The stated purpose matches conversation-analysis orchestration, and no explicit credential theft or external exfiltration is shown. However, the skill materially relies on unseen local scripts and multiple composed skills, creating a transitive trust boundary with unverifiable provenance and moderate autonomous behavior.
Confidence: 79%Severity: 61%
Audit Metadata