Paratran Transcription
Warn
Audited by Snyk on Feb 16, 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 accepts arbitrary, user-provided audio via its REST POST /transcribe endpoint and its MCP server (uploaded files), which are untrusted third-party inputs that get transcribed and delivered to the agent and could enable indirect prompt injection.
Audit Metadata