audience-research
Warn
Audited by Snyk on Jun 23, 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). The skill’s runtime workflow explicitly ingests “comments on recent posts” and “link-in-bio pages and creator shops” (public/outsider-authored text) via profile/content endpoints, which can include arbitrary free-form text from non-operating users into the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata