create-branch

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided input (branch names and issue numbers) which is interpolated into shell commands for git and gh tools.
  • Ingestion points: User-provided branch name strings and issue identification numbers.
  • Boundary markers: None explicitly defined for the interpolation.
  • Capability inventory: The skill uses the Bash tool to execute git status, git branch, git checkout, git push, git ls-remote, and gh issue commands.
  • Sanitization: The skill defines robust validation logic for branch names, including lowercase conversion, enforcement of kebab-case, length validation, and the rejection of special characters (e.g., ~, ^, :, ?, *, [, ], \, @{, ..) and non-ASCII characters. This significantly mitigates the risk of command injection via the branch name input.
  • [COMMAND_EXECUTION]: The skill performs standard repository management operations using well-known tools (git and gh). All network operations are directed at the repository's configured origin (typically GitHub), which is a trusted service. No privilege escalation or persistence mechanisms are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 06:07 PM