paw-pa-intake

Warn

Audited by Snyk on Jul 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.65). Outsider free text enters the LLM context when the user provides a public URL for audio/video, because scripts/transcribe.py passes that URL to AssemblyAI and writes the resulting diarized transcript as readable transcript.md which the agent then reads for structured extraction.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 25, 2026, 03:55 AM
Issues
1
Security Audit — snyk — paw-pa-intake