resource-curator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to click/fetch and "skim the content" from public third‑party sites (e.g., developer.mozilla.org, YouTube, dev.to, freecodecamp.org and other arbitrary URLs) as part of its link-audit and resource-finding workflow, so it will ingest untrusted open-web/user-generated content.