brand-research
Warn
Audited by Snyk on Jun 25, 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 3/5 web research and asset sourcing fetches public web pages/URLs at runtime (outsider-authored content) and then writes their extracted prose/metadata into
brand-research/*.mdandbrand-research/asset-urls.md, which the agent’s LLM uses to generate the pack.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata