generate-judge-problems
Warn
Audited by Socket on Sep 11, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill's purpose and capabilities mostly align, and there is no clear credential theft or exfiltration path. Risk comes from auto-trusting mise config and running unpinned external tooling via bunx/mise, which is more install-trust exposure than a pure documentation skill but not fundamentally incompatible with the stated problem-authoring workflow.
Confidence: 90%Severity: 58%
Audit Metadata