fetch

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and EXAMPLES.md explicitly require providing arbitrary public URLs via the fetch API's "url" parameter (examples include bit.ly, target-site.com, and public APIs) and show the agent fetching and parsing returned HTML/JSON (e.g., extracting titles, parsing JSON, or deciding to fall back to the Browser), so untrusted third‑party content is ingested and can influence subsequent actions.