design-doc-mermaid

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

• Third-party content exposure detected (high risk: 0.90). The skill's required "Resilient Workflow" and "Error Recovery Priority" in SKILL.md explicitly instruct the agent to search external public sources (e.g., "Search External", "perplexity_ask", "brave_web_search", "WebSearch") and use those results to apply fixes and retry diagram generation, meaning the agent will fetch and act on untrusted third‑party web content.