create-issues

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 fetch and review open GitHub issues (see "Open issues: !gh issue list --state open --limit 10" and Phase 1 "Review open issues to identify duplicates or related work"), which are user-generated, potentially public content that the agent is expected to interpret and that can influence creation/linking/labels—exposing it to indirect prompt injection.