minicpm5-finetune-unsloth
Fine-tune MiniCPM5-1B with unsloth for tight-VRAM single-GPU LoRA / QLoRA. Use when the user wants "unsloth", "FastLanguageModel", QLoRA on a 24 GB consumer GPU, or asks for the smallest VRAM footprint.
72
88%
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.
1 low severity finding. 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
The workflow reads the runtime-provided `DATA` jsonl file (`rows = [json.loads(l) for l in open(DATA, ...)]`), turns outsider-authored message `r["messages"]` into free text via `tok.apply_chat_template(...)`, and feeds it into the LLM/training context through the TRL `train_dataset`/`dataset_text_field="text"` pipeline; if `DATA` isn’t user-authored, this is an indirect prompt-injection channel.
- Repository
- OpenBMB/MiniCPM
- Commit
719e4fc
- 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.