afa-creative
Warn
Audited by Snyk on May 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly requires ingesting and using external public site and social media content—e.g., the Context Matrix lists
store_url("用于核对素材承接页") and the Brand Kit template notes "品牌网站 URL(用于提取视觉风格)" and Mode 1 Step 1 requires collecting "网站截图、社交媒体、产品图"—which the agent must read and use to drive prompts and creative decisions, exposing it to untrusted third‑party content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata