mcore-linting-and-formatting
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of local shell commands to perform code formatting and linting. Evidence includes instructions to run bash tools/autoformat.sh and use the uv run isort command within the Megatron-LM project environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process source code files, which constitutes a potential ingestion surface for untrusted data. Ingestion points: Python source files targeted for linting. Boundary markers: None explicitly mentioned in the skill instructions. Capability inventory: Execution of project shell scripts and dependency management tools. Sanitization: Reliance on standard linting tools which are designed for style enforcement rather than instruction parsing.
Audit Metadata