pricing-update

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md instructs the runtime to fetch and read the full contents of https://cursor.com/docs/models-and-pricing.md (first-party external text) before generating the pricing_supplement.json diff and PR, so outsider-authored content is ingested via a required network fetch.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching and reading remote content at runtime from https://cursor.com/docs/models-and-pricing.md as the canonical source that directly controls what pricing and alias updates to make, so this external URL is a required runtime dependency that controls agent behavior.