pytorch-fsdp2
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides links to official technical documentation and code samples from the PyTorch project (docs.pytorch.org) and associated GitHub repositories (github.com/pytorch).
- [COMMAND_EXECUTION]: Instructions describe the use of the 'torchrun' CLI tool, which is the standard utility for initializing and managing distributed PyTorch training jobs.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for an agent to modify existing training scripts, creating a surface for data ingestion. Ingestion points: Existing training scripts and environment variables such as LOCAL_RANK. Boundary markers: None explicitly defined in the instructions. Capability inventory: File writing (modifying training scripts) and process execution (torchrun). Sanitization: The process relies on standard PyTorch API behavior and developer review of generated training code.
Audit Metadata