webcraft-direction

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

• Third-party content exposure detected (medium risk: 0.30). The workflow instructs the agent to fetch upstream guidance skills from GitHub repositories (emilkowalski/skills and jakubkrehel/skills), exposing the agent to outsider-authored free text via GitHub content retrieval.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs fetching external skills from https://github.com/emilkowalski/skills and https://github.com/jakubkrehel/skills at runtime as behavioral instructions for motion and UI guidance.