trl-fine-tuning
TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.
59
70%
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.mdW011: 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 runtime workflow loads training prompts/completions from user-controlled Hugging Face datasets (e.g., via `load_dataset(...)`) and then feeds those prompt texts into TRL trainers (SFTTrainer/DPOTrainer/RLOOTrainer/GRPOTrainer), so outsider-authored free text can be ingested indirectly at training time without selecting a specific item first.
- Repository
- NousResearch/hermes-agent
- Commit
68fa7e9
- 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.