github

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly runs GitHub commands that fetch and display issue bodies and comments from repositories (see LIST_ISSUES.md and VIEW_ISSUE.md which call gh issue list and gh issue view), which are untrusted, user-generated third-party content the agent is expected to read and interpret.