skill-creator

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads and evaluates outsider-submitted trigger queries via evals/trigger-eval.json and runs evaluation scripts.

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

• Potentially malicious external URL detected (high risk: 0.70). The repository includes a dependency on https://fonts.googleapis.com and https://cdn.sheetjs.com in eval-viewer/viewer.html and assets/eval_review.html, which are unverified external operational dependencies fetched at runtime.