skills/flora131/atomic/gh-create-pr/Gen Agent Trust Hub

gh-create-pr

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Git and GitHub CLI (gh) commands to manage the development workflow. These commands are used for their intended purpose, such as checking branch status, viewing diffs, committing code, and managing pull requests.
  • [DYNAMIC_CONTEXT_INJECTION]: The skill employs dynamic injection (!command) to retrieve live repository data, including git status, current branch name, recent commit history, and existing pull request metadata. These operations are benign and serve to provide the agent with necessary context for the task.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local environment, such as Git diffs and PR descriptions. While this presents a surface for indirect prompt injection where malicious code comments could attempt to influence the generated PR text, the risk is considered low and managed by the agent's standard operational constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 10:59 PM