ml-training-recipes
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches specialized CUDA kernels from the
kernels-communityrepository on GitHub for optimized transformer attention calculations (references/architecture.md). - [EXTERNAL_DOWNLOADS]: Downloads pretrained protein language models from Hugging Face's official repository using the
transformerslibrary (references/biomedical.md). - [COMMAND_EXECUTION]: Recommends using standard
gitcommands (commit,reset) to track and revert model training experiments in a systematic loop (references/experiment-loop.md). - [COMMAND_EXECUTION]: References standard command-line tools for the
nnUNetv2framework to automate biomedical image segmentation workflows (references/biomedical.md). - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection due to its handling of external data and libraries.
- Ingestion points: Processes SMILES strings, protein sequences, EHR data, and raw text chunks during model training and tokenizer creation (
references/biomedical.md,references/experiment-loop.md). - Boundary markers: The provided examples do not use explicit delimiters to isolate external data inputs within prompts.
- Capability inventory: Employs dynamic kernel loading, CLI tool execution, and JIT compilation using
torch.compile. - Sanitization: No specific sanitization or input validation logic is included in the reference implementations.
Audit Metadata