greenfield
Warn
Audited by Snyk on Mar 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The workflow's mandatory steps explicitly perform "WebSearch for competitors" (step 2
/web-research) and "WebFetch top sources, extract key findings" (step 3/deep-research) from public web sources, meaning the agent will ingest and act on untrusted third-party content that can influence decisions.
Audit Metadata