split-pr
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh) and Git to perform operations such as viewing PR details, analyzing diffs, and managing branches and commits. - [DATA_EXPOSURE]: The skill reads repository configuration files like
.github/CODEOWNERSand PR metadata from the NVIDIA/Megatron-LM repository. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external data from pull requests.
- Ingestion points: Pull request titles, descriptions, and code diffs fetched via
gh pr viewandgh pr diffin SKILL.md. - Boundary markers: None provided; the agent processes the PR content directly without specific markers to distinguish between instructions and data.
- Capability inventory: The skill uses
git applyto modify local files andgit push/gh pr createto interact with remote repositories (SKILL.md). - Sanitization: There is no explicit sanitization or filtering of the PR content described in the workflow.
Audit Metadata