plan-jira-ticket

Warn

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directly interpolates the $ARGUMENTS variable into shell commands for acli and git without quoting or sanitization, creating a risk of command injection if shell metacharacters are included in the ticket ID.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting untrusted data from Jira tickets.
  • Ingestion points: Data retrieved from Jira via acli jira workitem view.
  • Boundary markers: Absent; the skill does not use delimiters or instructions to ignore commands within the ticket body.
  • Capability inventory: The agent can modify Jira ticket statuses and manage local/remote git branches.
  • Sanitization: No validation or escaping is performed on external ticket content before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 07:49 PM