skills/wkentaro/dotfiles/make-branch/Gen Agent Trust Hub

make-branch

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard git commands (git branch, git log, git diff, git stash, git switch, git reset, git push) to manage the local and remote development environment. These operations are essential to its function as a developer productivity tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes external data including commit messages and code diffs to generate suggested branch names. While this represents a potential surface for indirect prompt injection, the instructions limit the output to well-formed branch names using a specific kebab-case format, which naturally mitigates the risk of executing malicious commands embedded in the data.
  • Ingestion points: git log and git diff outputs are read to analyze work history.
  • Boundary markers: The skill provides a specific format for the generated branch name (<type>/<short-kebab-description>).
  • Capability inventory: Shell execution of git commands is the primary capability.
  • Sanitization: The instructions explicitly define the format and structure of the output strings used in subsequent commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 09:57 PM
Security Audit — agent-trust-hub — make-branch