models-dev-query

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch live, public data from models.dev (via https://models.dev/api.json and the GitHub API endpoints like repos/anomalyco/models.dev/contents/...) and to read/interpret those third‑party TOML/JSON files to choose models and generate API/configuration snippets, so untrusted external content can directly influence actions.