speech-to-text
Warn
Audited by Snyk on Jul 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow transcribes audio from a user-supplied external URL (e.g.,
audio_url/video_urlin SKILL.md), and the resulting transcript text is then ingested into the agent’s LLM context via the CLI app output—this transcript is derived from outsider-authored content (public web media) and can include free-form text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata