jira-expert

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows security best practices for Jira administration. The provided Python scripts (board_optimizer.py, issue_quality_checker.py, workflow_analyzer.py) are strictly offline tools that process local JSON data provided by the user. They do not perform any network requests, file system modifications, or dynamic code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by processing Jira export files. While this creates a theoretical path for indirect prompt injection if the processed Jira data contains malicious instructions, the risk is minimal as the scripts produce structured reports and do not have any exploitable side effects like network access or privilege escalation.
  • Ingestion points: scripts/board_optimizer.py, scripts/issue_quality_checker.py, and scripts/workflow_analyzer.py read user-supplied JSON files via input arguments.
  • Boundary markers: The scripts output human-readable text or structured JSON to the agent context without explicit 'ignore embedded instructions' delimiters.
  • Capability inventory: The skill's scripts have no capabilities for file writing, network communication, subprocess spawning, or dynamic code execution.
  • Sanitization: The scripts perform quality checks using regular expressions for process adherence but do not specifically filter for prompt injection payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 07:06 PM