kata-check-issues

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly queries and loads GitHub issues (see "list_issues" step using gh issue list and "load_context"/"execute_action" steps using gh issue view), which are untrusted, user-generated third‑party content that the agent reads, writes into local issue files, and uses to drive decisions and actions (pull-to-local, mode selection, moving issues, labels, and executing tasks).