acos-visual-gen
Warn
Audited by Snyk on Jun 14, 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). Runtime path: the skill performs
WebSearch("{topic} facts key information 2026")and then “Extracts 3-5 verifiable facts” from the fetched web content, which is outsider-authored free text that is ingested into the constructed LLM prompt for image generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata