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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 29, 2026, 03:37 AM
Issues
1