x-tweet-by-handle

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

• Third-party content exposure detected (high risk: 0.95). SKILL.md’s required workflow navigates to X profile pages and then uses browser-act network request <id> to save and parse the GraphQL response body (which contains outsider-authored tweet text) into JSON, which is then returned to the agent/LLM context as text/description fields.