x-api

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and formats public, user-generated tweets from X (see scripts/get_user_tweets.py and scripts/search_tweets.py which call https://api.x.com/2 and return tweet text/media), so the agent reads/interprets untrusted third‑party social-media content as part of its workflow, exposing it to possible indirect prompt injection.