simpo-training
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
64
78%
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
Fix and improve this skill with Tessl
tessl review fix ./06-post-training/simpo/SKILL.mdLow
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 training workflow loads outsider-authored free-text preference datasets from public HuggingFace datasets (e.g., `HuggingFaceH4/ultrafeedback_binarized`, `argilla/...`) whose `prompt/chosen/rejected` fields become readable text for the training pipeline at runtime, which is then ingested into the LLM context during forward passes.
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 README's installation instructs "git clone https://github.com/huggingface/alignment-handbook.git" followed by "python -m pip install .", which fetches remote code and executes it during setup (https://github.com/huggingface/alignment-handbook.git).
- Repository
- Orchestra-Research/AI-Research-SKILLs
- Commit
773a529
- 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.