twitter-intel

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public, user-generated tweets from Twitter/X using rnet_twitter.py's search_tweets (see "Phase 1 — Run Search" and cookie guidance pointing to x.com), then reads and analyzes that content (filtering, alerting, LLM-driven theme/categorization and cron-triggered actions), so untrusted third-party content can influence tool decisions and next actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs at runtime to re-extract the rotating SearchTimeline GraphQL ID from https://abs.twimg.com/responsive-web/client-web/main.*.js, meaning it fetches remote JS during operation and those fetched values directly control how the agent constructs/executes its GraphQL search requests, a required dependency for functionality.