build-minecraft-model-from-image
Warn
Audited by Snyk on Nov 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads a user-supplied local picture and the skill's own scripts and references, but Hard rule 43 tells the agent to search reference views on the web when the picture is insufficient, so outsider-authored web content can enter the context only after the agent actively searches for it.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata