sast-rce
Warn
Audited by Socket on Sep 20, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill is internally coherent as an RCE-audit workflow and does not exfiltrate data, request credentials, or install opaque tooling. However, it gives an AI agent explicit offensive security capability to discover and help validate RCE flaws, so it carries elevated risk despite otherwise proportional local-only behavior.
Confidence: 89%Severity: 66%
Audit Metadata