brand-storytelling
Warn
Audited by Snyk on Jun 21, 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). The skill’s runtime context is populated from
references/guest-insights.md, which contains long-form quotes and commentary authored by third parties (“30 guests”), i.e., outsider-authored free text that the agent will ingest as reference material.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata