minicpm5-finetune-llamafactory
Fine-tune MiniCPM5-1B with LLaMA-Factory (YAML-driven SFT / DPO / WebUI). Use when the user wants to fine-tune via LLaMA-Factory, llamafactory-cli, mentions YAML configs, WebUI, or asks for the most-documented community framework.
71
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.
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’s required workflow reads outsider-authored dataset free text from `${DATA_DIR}/your_data.jsonl` (messages `content` strings) into the training pipeline/LLM context via the LLaMA-Factory YAML dataset_dir/dataset mapping, so any non-user-authored dataset text could be ingested.
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 loads the external model "openbmb/MiniCPM5-1B" at runtime (from_pretrained) and explicitly delegates prompt templating to the model's own chat_template.jinja, so content from the external model repo (openbmb/MiniCPM5-1B) directly controls prompts.
- 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.