deep-research
Warn
Audited by Snyk on Jun 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The required runtime workflow for the deep phase (
/research-deep→deep-pipeline.md) delegates each item’s investigation to the web-search agent, which performs web fetch/search and reads outsider-authored free text from routed public sources (e.g., GitHub Issues, Stack Overflow, blogs, academic sites) into the agent’s LLM context as retrieved page/snippet content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata