bird-twitter-moderation

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches and reads tweet/thread content via bird read TWEET_ID --json / bird thread TWEET_ID --json (and likely mention fetching in the runbook), which is outsider-authored free text from X at runtime and is ingested into the agent’s LLM context for moderation decisions.