x-twitter-browser-ops

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses browser response observers to parse GraphQL list responses from X/Twitter endpoints (e.g., /followers, /following, /followers_you_follow, /verified_followers), which contain free-form user profile text authored by outsiders and are ingested into the agent’s LLM context via parsed user objects.