jira-automation

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow reads outsider-authored free text from Jira issues/issue comments when the user supplies inputs like jql and the workflow calls JIRA_SEARCH_FOR_ISSUES_USING_JQL_POST and (optionally) JIRA_GET_ISSUE/JIRA_LIST_ISSUE_COMMENTS, which ingest the issue/comment bodies authored by external Jira users.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). This skill requires adding and querying the external MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch tool schemas and connection/auth flows that directly determine the agent's available tools and behavior.