fine-tuning-with-trl
TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.
61
75%
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 ./optional-skills/mlops/training/trl-fine-tuning/SKILL.mdLow
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
This skill’s required runtime workflow includes loading a dataset from an external source (Hugging Face hub) via `datasets.load_dataset(...)`, which ingests outsider-authored free-form text from the dataset into training samples that are fed to the LLM for generation/rewarding (template: `templates/basic_grpo_training.py` line 48, plus prompt construction line 57).
- Repository
- NousResearch/hermes-agent
- Commit
4c9628e
- 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.