hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
70
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
SKILL.md instructs using `hf_jobs()` with a `script` that can be a **URL** (public web content), and that content/script text is then executed during the job (so any outsider-authored free text contained in the fetched script or dataset inspection output can reach the runtime context); additionally, the dataset inspector workflow explicitly fetches sample row text from the **remote, outsider-authored HF dataset** via the Datasets Server API.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill contains examples that fetch and execute remote scripts at runtime (e.g., hf_jobs calling https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py and https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py), and the GGUF conversion script clones and builds code from https://github.com/ggerganov/llama.cpp.git at runtime, so these external URLs directly provide code that will be executed during job runtime.
- Repository
- synthetic-sciences/openscience
- Commit
3a6c3a9
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.