polishing-issues

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches GitHub issue content using the gh issue view <number> --repo <owner/repo> --json title,body,labels,state,comments step, which ingests user-generated, public GitHub issue bodies and comments (untrusted third-party content) that the agent is expected to read and act on, enabling indirect prompt injection.