power-iterate
Warn
Audited by Socket on Oct 7, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is internally coherent as an autonomous iteration workflow, but its defining behavior is to let the agent act continuously without per-action confirmation. That autonomy is disproportionate for a generic development helper even without credential theft or external exfiltration, so overall risk is medium-high while malware evidence remains low.
Confidence: 84%Severity: 69%
Audit Metadata