pull-request

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes dynamic context injection (the ! syntax) to execute several local commands: git branch, git log, git diff, and git status. These executions are limited to gathering information about the current repository state to assist in drafting the PR.
  • [COMMAND_EXECUTION]: It instructs the agent to use git push and gh pr create (GitHub CLI) to perform the intended actions. These are standard, well-known development tools and their usage here is consistent with the skill's stated purpose.
  • [PROMPT_INJECTION]: The agent is instructed to analyze data from git log and git diff. While these sources could technically contain malicious instructions (indirect prompt injection) if an attacker has contributed to the repository, this is a standard risk for any tool processing version control data. The skill does not contain any direct prompt injection attempts to bypass safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 01:43 PM