x-tweet-search-by-query

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

• Third-party content exposure detected (high risk: 0.85). Yes—during network request <request_id> the skill saves and parses GraphQL SearchTimeline responses that include outsider-authored tweet text (and user bios/descriptions) into JSON via scripts/parse-tweets.py, which then becomes LLM-readable output in the agent context.