publish
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard version control commands (
git status,git fetch,git push,git diff) and GitHub CLI commands (gh pr view,gh pr edit). These operations are consistent with the skill's stated purpose of publishing commits and managing pull requests. - [INDIRECT_PROMPT_INJECTION]: The skill ingests content from local files such as
pull_request_template.mdand the provided template files in thetemplates/directory. While this is an ingestion point for external data, the content is strictly used as a skeleton for generating pull request descriptions and is not executed as code or instructions to the agent's core logic. - [PROMPT_INJECTION]: The instructions contain standard guidance for the agent's workflow. The use of the 'IMPORTANT' tag is benign and serves to ensure the agent reads the template file before proceeding with the PR creation. No attempts to override safety filters or bypass system instructions were detected.
Audit Metadata