apex

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

• Third-party content exposure detected (high risk: 0.90). The skill's Analyze and init workflows explicitly launch "general-purpose" subagents to perform web searches and fetch library docs (steps/step-01-analyze.md) and also support loading GitHub issues via gh issue view when -f is used (step-01 "Load Prior Context" and step-00-init), meaning it ingests public, user-generated web content that can be interpreted and directly influence planning and execution decisions.