onboarding-docs

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly instructs verifying developer experience best practices "via MCP servers (perplexity)" and references external public resources (e.g., GitHub repos, docs sites, Stack Overflow) that the agent would consume and read as part of its workflow, exposing it to untrusted third‑party content.