issue-triage

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly runs gh issue view $ARGUMENTS --json title,body,labels,author and then reads and acts on the GitHub issue body/title (user-generated, public content) to classify, reproduce, and decide fixes/PRs, so untrusted third-party content can influence actions.