graphite
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for standard development workflows. No security issues were identified during the analysis of the commands or the instructional content.
- [COMMAND_EXECUTION]: The skill uses allowed-tools to execute git, graphite, and github cli commands. These commands are scoped to repository management tasks such as branching, rebasing, and PR creation, which aligns with the skill's stated purpose.
- [DATA_EXFILTRATION]: No evidence of unauthorized data exfiltration was found. The skill interacts with local git repositories and remote GitHub repositories as expected for a version control tool.
- [PROMPT_INJECTION]: The instructions do not contain patterns designed to bypass AI safety guidelines or override system prompts. All instructions are focused on providing guidance for using the Graphite toolset.
Audit Metadata