create-branch

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill follows security best practices for git operations and shell command construction. It specifically instructs the agent to avoid shell interpolation of user-provided text and to use quoted arguments.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from git diffs and user-provided arguments to generate branch names, creating a potential surface for indirect prompt injection.\n
  • Ingestion points: Data enters the context via git diff output and the $ARGUMENTS variable.\n
  • Boundary markers: The skill includes explicit instructions to validate the generated branch name using git check-ref-format --branch and to treat user text as quoted arguments.\n
  • Capability inventory: The skill has the ability to execute git commands (checkout, branch, stash) and interact with the GitHub API via the gh CLI.\n
  • Sanitization: Branch names are strictly limited to ASCII letters, digits, and hyphens (kebab-case) and undergo validation before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 10:57 AM