x-research

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires using the twitter CLI to search and read public X/Twitter tweets, threads, replies and links (e.g., "Search using twitter cli" and steps to read threads and quote whole tweets), so the agent ingests untrusted, user-generated third‑party content from the open web that can influence its conclusions and actions.