happy-scribe
Warn
Audited by Snyk on Mar 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md shows explicit actions to retrieve user-generated transcripts/exports from Happy Scribe (e.g., "Get Transcription", "Get Export", and the Membrane proxy request examples) which cause the agent to fetch and read third-party user content from the Happy Scribe API that could contain instructions and influence subsequent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata