peft-fine-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external datasets for fine-tuning purposes, which introduces an attack surface for instructions embedded in data.
- Ingestion points: External datasets are loaded using the
datasets.load_datasetfunction inSKILL.md(e.g., "databricks/databricks-dolly-15k"). - Boundary markers: The code utilizes delimited prompt templates (e.g., "### Instruction:", "### Response:") to separate fields, which helps mitigate instruction confusion.
- Capability inventory: The skill utilizes
transformers.Trainerandmodel.save_pretrainedwhich perform write operations to the local file system. - Sanitization: No explicit sanitization or filtering of the dataset content is described before the tokens are processed by the training loop or saved to disk.
- [EXTERNAL_DOWNLOADS]: The skill documentation includes commands to fetch code and models from external remote sources.
- Fetches packages from official registries via
pip install peft transformers bitsandbytes. - Downloads pre-trained models and datasets from the Hugging Face Hub (e.g., "meta-llama/Llama-3.1-8B").
- Provides instructions in
references/troubleshooting.mdto download source code for manual compilation fromgithub.com/TimDettmers/bitsandbytesto resolve CUDA environment issues.
Audit Metadata