whisper
Warn
Audited by Socket on Sep 22, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's actual behavior is a Pixazo gateway integration for speech-to-text, but its stated purpose repeatedly claims image generation/editing via OpenAI Whisper, which is materially false. Credential collection/storage is proportionate to an API integration, yet the key is routed to a third-party gateway rather than OpenAI, and the wildcard transitive skill-install instruction adds unnecessary trust expansion.
Confidence: 92%Severity: 71%
Audit Metadata