developer-workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to "use MCP tools (WebSearch, Fetch) to clarify implementation details" in the Agent Startup Protocol step 3, meaning it will fetch and interpret open web content (potentially user-generated/untrusted) as part of its workflow and decisions, creating a clear avenue for indirect prompt injection.