mcp-ecosystem-optimizer

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes browsing public MCP registries at runtime (e.g., Glama AI, Official MCP Registry, PulseMCP) and using /github-gem-seeker to search GitHub, which can ingest outsider-authored free text from those web pages/search results into the agent’s LLM context.