apex-tier1
Warn
Audited by Socket on Mar 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is purpose-aligned for autonomous coding, but its core design enables unsupervised write/execute behavior plus remote git push and PR creation. Install trust is mostly normal and no clear exfiltration is shown, yet the zero-intervention workflow makes it a medium-risk automation skill rather than a benign documentation/helper skill.
Confidence: 89%Severity: 58%
Audit Metadata