elevenlabs-stt
Warn
Audited by Socket on Jul 23, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated STT purpose is coherent, but the trust chain is not clean. The skill asks the agent to install another skill (`belt-sh/cli`), references mutable raw GitHub install docs, and does not cleanly match the official inference.sh Belt distribution paths, while also requiring credentialed remote uploads of user audio/text.
Confidence: 82%Severity: 74%
Audit Metadata