apollo-mcp-server

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow (SKILL.md and references) instructs the agent to use built-in introspection and execute tools that fetch and read schema/operation data from configured GraphQL endpoints and GraphOS uplink/collections (e.g., the endpoint, schema: source: uplink, operations: source: collection and execute/introspect tool examples), which clearly ingests third-party API content that can influence subsequent tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The Quick Start includes installation commands that fetch and execute remote code at runtime (curl -sSL https://mcp.apollo.dev/download/nix/latest | sh and iwr 'https://mcp.apollo.dev/download/win/latest' | iex), which directly executes remote code and is required to install/run the MCP server.