atlassian-cli

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests user-generated Jira content from arbitrary Atlassian hosts (e.g., via --site mysite.atlassian.net and commands like "acli jira workitem search/view/comment-list") and its recipes use those results to drive follow-up actions (bulk transitions, assignments), so untrusted third-party content can materially influence tool use.