ln-650-persistence-performance-auditor

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

• Third-party content exposure detected (high risk: 0.80). The skill's mandatory research rules (references/evaluation_research_contract.md and references/research_tool_fallback.md) require using WebSearch/WebFetch and external MCP tools to fetch and interpret public web documentation and community sources, so the agent will ingest untrusted third-party web content that can influence audit decisions and subsequent tool/worker actions.