hugging-face-model-trainer
Train or fine-tune TRL language models on Hugging Face Jobs, including SFT, DPO, GRPO, and GGUF export.
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
The workflow allows fetching and processing arbitrary Hugging Face datasets (such as via dataset inspection or training scripts) which contain untrusted outsider-authored text.
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 instructs agents to fetch external Python scripts (such as `https://huggingface.co/datasets/mcp-tools/skills/raw/main/dataset_inspector.py`) via `uv run` or `hf_jobs()`, which are then executed as runtime code, satisfying the criteria for an unverifiable remote external dependency.
- Repository
popey/claude-code-skills
- Revision
a5a6601
- 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.