knowledge-orchestrator

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

• Third-party content exposure detected (high risk: 0.80). The skill's MCP integration documentation (references/mcp_integration.md and references/mcp_integration.md examples) explicitly calls WebSearch and mcp__obsidian-dev__search-docs to fetch domain research and examples from the open web and expects the agent to load and interpret that external content as part of context enrichment/workflows, exposing it to untrusted third-party input.