understanding-code-context

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow calls Context7 tools (resolve-library-id and get-library-docs) to fetch external library documentation and explicitly permits falling back to WebSearch when docs are missing (see SKILL.md, reference/tools.md, and Troubleshooting), so the agent reads and applies third‑party public web content (including blog/StackOverflow fallbacks) that could contain arbitrary instructions influencing its actions.