cursor-ai-chat

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly allows registering arbitrary external URLs for @Docs ("Enter URL: https://react.dev/... (Cursor crawls and indexes it)") and supports @Web live web search, meaning the agent ingests and uses open/public third‑party content as part of its workflow which could carry untrusted instructions.