create-pr
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
gitandgh(GitHub CLI) to interact with the local repository and GitHub's API. These commands are necessary for the skill's stated purpose of managing pull requests. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) as it processes external data from the git history and code diffs to generate pull request descriptions.
- Ingestion points: Data from
git logandgit diffcommands inSKILL.mdis provided to the agent. - Boundary markers: There are no explicit delimiters used to isolate git-derived content from the agent's logic.
- Capability inventory: The skill can perform modifications on GitHub using
gh pr createandgh apias defined inSKILL.md. - Sanitization: No sanitization or validation of the commit history or code changes is performed before the data is processed by the agent.
Audit Metadata