jira-automation

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the configuration of a third-party MCP server endpoint located at https://rube.app/mcp. This introduces a dependency on external infrastructure managed by a vendor not included in the trusted providers list.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection attacks by ingesting untrusted content and executing actions based on it.
  • Ingestion points: Untrusted data enters the agent context through tools like JIRA_GET_ISSUE, JIRA_SEARCH_FOR_ISSUES_USING_JQL_POST, and JIRA_LIST_ISSUE_COMMENTS as described in SKILL.md.
  • Boundary markers: The instructions lack delimiters or explicit warnings to the agent to disregard instructions that may be embedded within Jira issue descriptions or comments.
  • Capability inventory: The skill includes tools for modifying the environment, such as JIRA_CREATE_ISSUE, JIRA_EDIT_ISSUE, JIRA_ADD_COMMENT, and JIRA_ADD_USERS_TO_PROJECT_ROLE (referenced in SKILL.md).
  • Sanitization: There are no documented procedures for sanitizing, filtering, or validating the content retrieved from Jira before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:58 PM
Security Audit — agent-trust-hub — jira-automation