jira-communication

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes user-generated Jira content — e.g., jira-issue.py's intent verbs (work / qa / qa-fail) call fetch_comments_paginated and include issue descriptions, comments, attachments and scraped URLs (see references/qa-gather.md and SKILL.md) so untrusted third-party prose from Jira issues can be read and directly influence downstream decisions or actions.