pronounce-button
Warn
Audited by Socket on Jul 27, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s purpose is coherent and its intended data flow to ElevenLabs is plausible, but its core behavior is outsourced to an unpublished local script that receives the ElevenLabs API key. That unverifiable credential-handling component makes the skill high risk despite otherwise proportionate file access and an official final API destination.
Confidence: 91%Severity: 84%
Audit Metadata