cowart-image-edit
Warn
Audited by Snyk on Aug 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md workflow step 1–2 has the agent read user-provided Cowart annotation screenshots at runtime and extract visible 批注 labels/arrows/edit notes from those outsider-supplied images (edit brief), which are then used to drive generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata