goose-graphics-create-style

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The skill workflow involves searching and listing community-published styles (npx gooseworks styles list/search/get), which reads community-contributed style manifests and names from the shared Gooseworks catalog registry.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to install an external package and download installation instructions from https://gooseworks.ai/install.md, but the domain provenance is unverified and third-party relative to standard package registries, rendering it a weak/unknown operational dependency.