create-pull-request
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various Git and GitHub CLI commands to gather project context and perform actions, such as
git log,git diff,git push, andgh pr create. These are standard operations for automating version control workflows. - [EXTERNAL_DOWNLOADS]: It provides instructions for the user to install the
ghCLI from trusted sources (cli.github.com or Homebrew) if it is not found. This is a legitimate prerequisite verification step targeting well-known services. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local environment to facilitate automated title and description generation, creating a surface for indirect instructions to be processed.
- Ingestion points: Metadata from
git log(commit messages),git diff(source code changes), and branch names inSKILL.md. - Boundary markers: The skill does not define strict delimiters or 'ignore' instructions for the data interpolated into the PR generation prompts.
- Capability inventory: The skill uses
git pushto upload code andgh pr createto submit formatted content to GitHub. - Sanitization: There is no evidence of sanitization for character encoding or instruction patterns within the ingested git history data before it is processed by the AI.
Audit Metadata