context7

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

• Third-party content exposure detected (high risk: 0.80). The skill queries the external Context7 API (e.g., https://context7.com/api/v2/libs/search and /api/v2/context) to fetch public documentation snippets from third‑party websites, which the agent reads and uses—exposing it to untrusted, user/website‑provided content that could carry indirect prompt injection.