aesthetic-research
Warn
Audited by Snyk on Jul 7, 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). SKILL.md Step 3/4/5 requires runtime searching of public image sources (e.g., Pinterest/Dribbble/Behance/Google Images) and saving results, which typically involves ingesting outsider-authored page text/metadata (free-form) into the agent’s context during browsing/search.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata