deep-research
Warn
Audited by Snyk on Aug 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In Step 2–4, the workflow ingests outsider-authored free text by running web search (ddgs or web-forager CLI) over user queries and then fetching selected URLs’ full page content for the LLM to synthesize.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata