jira

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and parses user-generated content from external Jira instances (see SKILL.md commands like "issue comments" and the scripts/jira.py functions search_issues, get_issue, and get_comments which retrieve and extract comment bodies and issue fields), so third-party Jira comments/issue text could be read and influence agent decisions.