collect
Warn
Audited by Socket on Mar 28, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill's purpose broadly matches its behavior, but it is high-trust automation that fetches untrusted external content, lets subagents analyze/write based on that content, and sends outbound notifications automatically. The main concerns are autonomous real-world actions and indirect prompt-injection exposure, not clear malware or credential theft.
Confidence: 87%Severity: 69%
Audit Metadata