moai-cc-mcp-plugins

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

• Third-party content exposure detected (high risk: 0.80). The skill's runtime configuration explicitly includes public-data integrations — e.g., the mcpServers entry "ai_search_intelligence" / "brave-search" in SKILL.md and templates/settings-mcp-template.json (BRAVE_SEARCH_API_KEY) and the "ai_github_enhanced" GitHub integration — which fetch and ingest open web/search and public repo content that the agent uses to influence design/optimization decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). This skill invokes npx to fetch and execute remote npm packages at runtime (e.g., "npx -y @anthropic-ai/mcp-server-github" and "@modelcontextprotocol/..." entries) and also references an external plugin repo https://github.com/your-org/claude-plugins, so remote content is fetched and executed as a required dependency.