ai-detecting-anomalies
Warn
Audited by Socket on May 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core anomaly-detection guidance is coherent and the DSPy/LM data flow matches the stated purpose, but the skill weakens trust by instructing installation from a personal GitHub repo via unpinned `npx skills add` and by recommending an additional transitive skill install from the same source. This is more a supply-chain and trust-boundary concern than confirmed malware.
Confidence: 87%Severity: 71%
Audit Metadata