minicpm5-finetune-ms-swift
Fine-tune MiniCPM5-1B with ms-swift (ModelScope's SFT / DPO / KTO / ORPO toolkit). Use when the user mentions "ms-swift", "swift sft", "swift rlhf", or wants ModelScope-native training. The two mandatory flags `--model_type llama --template chatml` are baked in.
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.
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
The required workflow feeds user-provided JSONL training data from `DATA` into ms-swift/transformer training (`swift sft --dataset "${DATA}"`), and if that JSONL contains outsider-authored free-text messages, that text will be read as training prose at runtime and thus placed into the LLM context during training; the skill itself is generic and does not sanitize/author-trust the dataset.
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's install step includes "pip install git+https://github.com/modelscope/ms-swift.git", which fetches and installs remote code from GitHub (executing third-party code as a runtime dependency), so it directly introduces execution of external code.
- 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.