issues

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill constructs shell commands using user-provided input for issue titles, bodies, and labels. Specifically, the instruction gh issue create --title "[title]" --body "[constructed body]" --label "[labels]" demonstrates direct interpolation of variables into a bash command. While the skill later recommends using HEREDOC to preserve formatting and improve safety, the initial pattern is vulnerable to command injection if a user provides a title or label containing shell metacharacters like backticks or subshells. To mitigate this, all user-controlled variables should be treated as untrusted data and wrapped in strict boundary markers or passed through the agent's safe execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 09:57 PM