mcp-gateway-configuration

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires MCP servers that access public/user-generated content—e.g., the "github" server (repository operations: issues, PRs, code search) and the "playwright" server (browser automation: navigate, click, screenshot), plus an SSE remote-HTTP example—so the agent is expected to fetch and interpret untrusted third-party web/social content as part of its workflow, which could enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill includes an SSE server configuration that connects at runtime to an external endpoint (https://mcp-server.example.com/sse), which would allow a remote MCP server to supply tool responses/instructions and thus directly control agent behavior or execute code.