jira-communication

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

• Third-party content exposure detected (high risk: 0.70). The skill auto-triggers on Jira URLs and issue keys (SKILL.md) and the CLI scripts (e.g., scripts/core/jira-issue.py, scripts/core/jira-search.py, scripts/core/jira-attachment.py) explicitly fetch and parse issue descriptions, comments, fields and attachments from configured Jira instances (user-generated/untrusted content) which the agent reads and can drive follow-up actions (searches, updates, downloads), creating a clear path for indirect prompt injection.