Podcast Transcription Pipeline
Warn
Audited by Snyk on Mar 29, 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 explicitly states the pipeline batch-processes RSS feeds via the podcast index API and fetches episodes (and integrates with Transistor.fm/Podbean APIs) to transcribe and analyze public podcast audio, so the agent ingests untrusted third-party content (podcast episodes) as part of its workflow which could contain instructions that influence downstream actions like summaries, chaptering, or automatic attachments.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata