market-research-brief
Warn
Audited by Snyk on Nov 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow has no mandated fetch of outsider content, but Step 1 asks the agent to determine data sources and the framework points to third-party data (e.g., trackers, platform reports), so the agent may search arbitrary web pages and ingest outsider-authored text, which is a low-risk path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata