food-research
Warn
Audited by Snyk on Jul 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required runtime workflow performs live retrieval of candidate studies via public/connected literature sources (e.g.,
source_scoutusing MCP/web search) and then reads their full-text PDFs/HTML for screening/extraction, which is outsider-authored free text being ingested into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata