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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 08:59 AM
Issues
1