jira-ticket-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection through user-supplied data.\n
  • Ingestion points: User-provided summary and description fields are processed by the agent and passed to the jira command in SKILL.md and scripts/create_ticket.py.\n
  • Boundary markers: The prompt instructions do not include delimiters or specific warnings to ignore embedded instructions within the user input.\n
  • Capability inventory: The skill has the capability to execute shell commands (jira-cli) and write data to an external Jira instance via scripts/create_ticket.py.\n
  • Sanitization: No explicit sanitization or filtering of the ticket content is performed before interpolation into the command structure.\n- COMMAND_EXECUTION (SAFE): The skill uses subprocess.run with an argument list in scripts/create_ticket.py, which is the recommended practice to prevent shell injection. Documentation examples also use quoted shell variables to mitigate basic command injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:20 PM