visualize-in-3d
Fail
Audited by Snyk on Nov 18, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill is a legitimate 3D-visualization workflow, but one line says a nightly sync script mirrors files from this folder to a public copy without saying what it sends, which could publish user-side material the user did not expect.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow has the agent search and fetch outsider-authored content, such as community-uploaded models on Sketchfab and Poly Pizza, OpenStreetMap data, Wikimedia Commons images, and web sources for facts, but none of it is pushed into a feed the workflow monitors, so an outsider cannot force delivery.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (medium risk: 0.30). The decisive dependency is
npx skills add codepawl/crucible, a GitHub repository locator run during setup whose installed skill instructions the agent is told to read before building recipes; CodePawl is credibly the project's own organization, but it is not an established vendor or enterprise publisher with a signature or digest, so the tier is common/reputable unofficial.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata