skills/yaklang/yakit/create-pr/Gen Agent Trust Hub

create-pr

Pass

Audited by Gen Agent Trust Hub on Nov 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git and the GitHub CLI (gh) to perform repository operations. It includes explicit defensive instructions to mitigate command injection risks, such as using single-quoted titles with character escaping and passing multi-line PR descriptions via temporary files instead of direct shell interpolation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git logs, commit messages, and external code-review outputs to generate PR content.
  • Ingestion points: Reads from .github/PULL_REQUEST_TEMPLATE.md, git log history, and the code-review skill output.
  • Boundary markers: PR bodies are handled via the --body-file flag to prevent shell interpretation of the content.
  • Capability inventory: The skill has permissions to push code to remote repositories and modify PR metadata on GitHub.
  • Sanitization: Employs temporary file storage and shell-safe quoting for dynamic inputs.
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing the GitHub CLI (gh) via official package managers like Homebrew or Winget if it is missing from the environment. This represents a safe reference to well-known tools from trusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 7, 2026, 08:59 PM