compare-models

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs the agent to fetch per-model docs and schemas from public Replicate URLs (e.g., https://replicate.com/{owner}/{model}/llms.txt) and to read model metadata/pricing from the Replicate website, which are third-party, community-provided pages that can directly influence model selection and subsequent actions.