creating-jira-subtasks

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through its reliance on the docs/<TICKET_KEY>-tasks.md file, which is used to populate Jira subtask summaries and descriptions.
  • Ingestion points: The subtask-creator.md subagent reads the local plan file to extract task objectives, notes, and requirements.
  • Boundary markers: None. The instructions do not specify the use of delimiters to isolate untrusted file content from the API payload structure.
  • Capability inventory: The skill possesses the capability to write to external Jira instances via MCP tools based on the parsed data.
  • Sanitization: No validation or sanitization is performed on the extracted task text before it is transmitted to the external Jira service.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 01:57 PM