read-x-links-local

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

• Third-party content exposure detected (high risk: 0.85). The required workflow takes a user-supplied URL (e.g., an X/Twitter status) and the runtime script scripts/read-x.ts fetches/expands that outsider-authored post/reply text from the public web into the agent/LLM context, which is classic indirect prompt injection via fetched free-form content.