design-jira-state-analyzer

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of pandas and an external CLI tool named jira-tool to perform analysis operations.
  • [COMMAND_EXECUTION]: Examples provided in the documentation use shell-based command execution via uv run and Python heredocs to aggregate data.
  • [PROMPT_INJECTION]: The skill ingests external data from workflow logs, which presents a risk of indirect prompt injection.
  • Ingestion points: Processes Jira changelogs and GitHub PR timelines extracted from external JSON files or API responses.
  • Boundary markers: No specific boundary markers or instructions are defined to distinguish external data content from agent instructions.
  • Capability inventory: The skill facilitates network requests to the Jira API and file system operations (read/write) for analysis reports.
  • Sanitization: The implementation is focused on temporal calculations and does not perform sanitization on string fields (like status names or author labels) found in external logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:23 PM