x-article-converter

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to "Use WebSearch to find Twitter/X handles" and to read public web/social media pages (Twitter/X and arbitrary sites) to extract handles, so it ingests untrusted, user-generated third-party content as part of its workflow.