NYC

jira-cli

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill requires the jira-cli tool from a third-party repository (github.com/ankitpokhrel/jira-cli). While this is a common open-source utility, the source is not within the predefined list of trusted organizations.
  • [PROMPT_INJECTION] (LOW): This skill has an indirect prompt injection surface. 1. Ingestion points: Untrusted data enters via jira issue view and jira issue list which fetch external summaries and comments. 2. Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the data. 3. Capability inventory: The skill has write capabilities including jira issue delete, jira issue move, and jira issue edit. 4. Sanitization: Absent; the skill does not include logic to escape or filter incoming Jira content.
  • [COMMAND_EXECUTION] (SAFE): The skill uses standard shell command patterns to interact with the installed CLI. Functional command substitution like $(jira me) is used appropriately for context-gathering.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:09 PM