backend-simplicity-engineer

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

• Third-party content exposure detected (high risk: 0.80). The skill's Phase 2 explicitly launches "codex-deep-research" and "gemini-research-analyst" subagents to research external resources (e.g., web/Google Gemini) and return findings, which means the agent will fetch and interpret untrusted public web content as part of its workflow.