edit
Warn
Audited by Socket on Oct 5, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core local ffmpeg/Python editing workflow is coherent and mostly benign, but the skill also instructs transitive installation of third-party skills and an optional git-cloned editable toolchain that receives an ElevenLabs API key. Those external routes are same-purpose and documented by upstream repos, so this is not confirmed malware, but the broadened trust chain and credential-forwarding make the overall skill medium/high risk.
Confidence: 90%Severity: 74%
Audit Metadata