brand-research
Warn
Audited by Snyk on Jul 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: 0.85). Phase 3 web research explicitly uses WebSearch/WebFetch to retrieve brand/trade-press/audience pages at runtime and then writes their contents into the LLM-generated
brand-research/*.mdfiles, so outsider-authored free text from public web pages can enter the agent’s LLM context via the web-fetch/research path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata