open-multi-agent-orchestration

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly shows MCP Server Integration using @modelcontextprotocol/server-github (via connectMCPTools) and agent tools like "search_repositories" / "create_or_update_file" to fetch and act on public GitHub repository content, which is untrusted, user-generated third‑party content that agents are expected to read and use to drive actions.