working-with-jira-acli

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: Provides instructions for executing shell commands using the acli utility to perform Jira management tasks.
  • Evidence: Command patterns for acli jira workitem create, edit, transition, and bulk operations in SKILL.md.
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified through the ingestion of untrusted data from Jira.
  • Ingestion points: Reads issue descriptions, summaries, and comments via acli jira workitem view and acli jira workitem search in SKILL.md.
  • Boundary markers: Absent. No specific instructions are provided to the agent to treat retrieved Jira content as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill enables the agent to create, edit, transition, and delete Jira work items, providing a mechanism for automated actions based on potentially malicious inputs.
  • Sanitization: Absent. Retrieved content is processed directly by the agent without validation or filtering.
  • [DATA_EXFILTRATION]: Facilitates the retrieval of organizational data from a Jira Cloud instance.
  • Evidence: Commands such as acli jira workitem search and acli jira project list allow access to internal work items and project metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 07:37 AM
Security Audit — agent-trust-hub — working-with-jira-acli