prioritize
Warn
Audited by Snyk on Jul 4, 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). Outsider free text can enter the LLM context via
research-agent’s runtime WebSearch/URL fetching path (public web pages/case studies are ingested as readable prose and then used downstream for initiative/ICE evidence).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata