gt
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- NO_CODE (SAFE): This skill contains purely markdown-based documentation and command references. There are no executable scripts, shell commands, or configuration files that could perform actions on the system.
- PROMPT_INJECTION (SAFE): While the skill uses strong instructional language (e.g., "CRITICAL", "MUST UNDERSTAND"), these are used in the context of explaining the tool's mental model and do not attempt to override the AI agent's safety constraints or system instructions.
- DATA_EXPOSURE (SAFE): The skill mentions internal configuration files for Graphite (such as
.git/.graphite_repo_config), but it does not attempt to access, extract, or transmit their contents. The mention is educational for understanding how the tool stores metadata locally.
Audit Metadata