capture-idea
Warn
Audited by Snyk on Jul 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The required workflow relies on “transcription MCP” to transcribe an MP3 note; the MP3’s audio content is not controlled by the skill’s bundled text and becomes readable free-form transcript text injected into the LLM context for spec generation, so any outsider-authored audio would propagate via the transcription step.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata