ContentAnalysis

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The ExtractWisdom workflow explicitly fetches transcripts and page content from public sources (Workflows/Extract.md Step 1: "fabric -y 'URL'" for YouTube and "WebFetch" for Article URL) and requires the agent to read and base dynamic section selection and actions on that untrusted, user-generated third‑party content, creating a clear path for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 11:02 PM