gh-issue

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions utilize the GitHub CLI tool (gh) for repository management. The provided examples demonstrate secure practices by using double-quoted arguments and quoted heredoc delimiters ('EOF') to prevent unintended shell expansion when handling dynamic issue content.
  • [PROMPT_INJECTION]: The skill defines a process for transforming untrusted or external information into GitHub issues, which constitutes an indirect prompt injection surface.
  • Ingestion points: Data enters the system via the issue title and body parameters of the gh CLI commands (SKILL.md).
  • Boundary markers: Present. Examples use shell quotes and heredoc delimiters to encapsulate the injected content.
  • Capability inventory: The skill possesses the capability to perform network-based write operations to GitHub repositories.
  • Sanitization: Absent. The instructions do not mandate specific filtering or validation steps for the input data, relying on the agent's interpretation of the template.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 05:51 PM
Security Audit — agent-trust-hub — gh-issue