mcp-setup

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md directly configures and recommends using "mcp-omnisearch" to perform web and GitHub searches and content extraction from public sites (Tavily, Brave, Kagi, Perplexity, GitHub), so the agent will ingest untrusted third-party/user-generated content that could contain instructions affecting its actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill's runtime config invokes npx to fetch and execute external MCP packages (e.g., https://github.com/spences10/mcp-omnisearch and related repos), so remote code is fetched and executed at runtime and relied upon as required dependencies.