global-chat-agent-discovery

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses the Global Chat MCP server to search across multiple external registries/web directory entries at runtime, so the agent ingests outsider-authored free text (e.g., registry listings/descriptions and endpoint details) returned by those public sources into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs agents to run "npx -y @global-chat/mcp-server", which fetches and executes remote npm package code at runtime (the MCP server is presented as the recommended, required programmatic dependency), so this is a runtime external dependency that executes remote code.