run-parallel-agents-feature-build

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs agents to perform "web browsing tasks" using the browse tool (e.g., "For web browsing tasks, use browse --session <agent-name>" in Step 4 and the Integration section), which implies fetching and interpreting open/public web content that could be untrusted and influence agent actions.