x-research

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 displays public, user-generated X/Twitter content (and linked web pages) via the X API (see scripts/x_api.py and references/x-api.md calling https://api.x.com/2/tweets/search/recent) and via the x_xai.py x_search tool, so the agent will read and interpret untrusted third-party posts and links that could carry indirect prompt injection.