design-to-issues

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to list labels, view repository information, create issues, and manage milestones. These commands are restricted to the local repository environment and use standard GitHub API interactions.
  • [EXTERNAL_DOWNLOADS]: No external downloads or remote scripts are used. All executable scripts (create_issue.sh, create_milestone.sh) are bundled within the skill directory.
  • [PROMPT_INJECTION]: The instructions provide a clear, task-oriented workflow without any attempts to bypass safety filters or override system instructions.
  • [DATA_EXFILTRATION]: No sensitive data access or external network exfiltration patterns were detected. Data movement is limited to reading local design documents and sending that content to the user's authenticated GitHub repository.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:43 AM
Security Audit — agent-trust-hub — design-to-issues