jira-automation

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a legitimate configuration guide and documentation for integrating Jira automation tools into an AI agent environment.
  • [EXTERNAL_DOWNLOADS]: The skill references https://rube.app/mcp as the MCP server endpoint. This is a functional requirement for the service and is presented transparently to the user for manual configuration.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials were found. Authentication is performed via a dynamic OAuth process mediated by RUBE_MANAGE_CONNECTIONS, adhering to security best practices.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes untrusted data from Jira issues and comments. * Ingestion points: Content retrieved via JIRA_GET_ISSUE, JIRA_SEARCH_FOR_ISSUES_USING_JQL_POST, and JIRA_LIST_ISSUE_COMMENTS. * Boundary markers: None identified in the provided instructions. * Capability inventory: Limited to Jira API tool slugs (e.g., JIRA_CREATE_ISSUE, JIRA_EDIT_ISSUE, JIRA_ADD_COMMENT). No system-level execution capabilities are requested or used. * Sanitization: No specific sanitization or filtering logic is described for the external Jira content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 06:13 PM