skill-management
Warn
Audited by Socket on May 19, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
This skill is coherent with its stated purpose, but it is medium risk because its main job is transitive installation of external skills. The official `npx skills add` path appears legitimate, yet the generic unpinned GitHub fallback and same-session prompt injection meaningfully raise trust and prompt-injection risk. No direct credential harvesting or overt malware behavior is present.
Confidence: 89%Severity: 62%
Audit Metadata