agent-architect

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1.5 "Research the Domain" explicitly instructs the agent to "Search for current best practices" and "look up documentation", and the referenced config (references/opencode-config.md) exposes webfetch/websearch tools, so the agent will fetch and read open/public third‑party web content that could carry untrusted/user‑generated input.