slash-commands

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Pattern 3: Multi-Agent Orchestration" explicitly instructs agents to "Use gh for GitHub interactions" to view issues, search for duplicates, and comment—meaning the agent will fetch and read user-generated GitHub content (untrusted third-party data) as part of its workflow.