webcraft-build

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

• Third-party content exposure detected (medium risk: 0.30). The workflow fetches GitHub repositories (emilkowalski/skills and jakubkrehel/skills), which exposes the agent to outsider-authored text via issue/PR descriptions, commit messages, or file contents in those repositories.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to fetch remote GitHub repositories (emilkowalski/skills and jakubkrehel/skills) at runtime to obtain instruction material and behavior-selecting configuration, constituting an unverifiable third-party operational dependency.