transcription-speech-to-text-hebrew

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required workflow processes audio and video files from third parties (including YouTube, social media, and local files) whose transcriptions contain untrusted free text ingested by the LLM.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill executes version_check.py during setup/runtime, which fetches version metadata from an uncontrolled personal/organization GitHub repository, creating an unverifiable remote dependency.