model-id-lookup

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches and ingests a public third-party JSON from https://models.dev/model-schema.json (see SKILL.md workflow and scripts/update_models.py), and the agent reads that data to determine and recommend model IDs—so external content can materially influence subsequent tool use and decisions.