Agentic Website Stack
Warn
Audited by Socket on Apr 17, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
BENIGN overall as a website automation skill: capabilities broadly match the stated purpose and data flows use expected official services. Security risk is still medium because the skill enables autonomous publishing, processes untrusted external content, and renders AI-generated HTML, which can lead to unsafe public actions or XSS if implemented as shown.
Confidence: 90%Severity: 64%
Audit Metadata