context7

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md "Core workflow" and references/context7.md) calls mcp__context7__query_docs (after resolving a library ID) to fetch current third-party library documentation and examples from public sources, which the agent will read and use to drive decisions and actions, exposing it to untrusted external content that could contain injected instructions.