giving-feedback
Warn
Audited by Snyk on Jul 16, 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). SKILL.md and its referenced artifacts/guest-insights embed outsider-authored free text (e.g., guest quotes and sourced excerpts from external people) into the skill’s runtime prompt context as static knowledge.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata