docs-search

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

• Third-party content exposure detected (high risk: 0.80). The skill's search command returns content snippets and source URLs from the Grounded Docs index and the workflow explicitly tells users to "index the docs first (see docs-manage skill)" to scrape documentation, meaning the agent will read/interpret potentially public third-party documentation (source URLs) as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime commands (e.g., "npx @arabold/docs-mcp-server@latest") fetch and execute remote npm package code from the registry, so it relies on external code that is executed at runtime.