slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
58
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/slime/SKILL.mdThe canonical home for this skill is slime-rl-training in Orchestra-Research/AI-Research-SKILLs
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 describes loading training prompts/labels from user-supplied JSONL files (e.g., `--prompt-data`), which become runtime free-text “prompt” content in the rollout/training flow—so if that JSONL contains outsider-authored text, it can be fed into the agent’s LLM context.
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 instructs users to fetch and install code from https://github.com/THUDM/slime.git (git clone followed by pip install), which fetches remote code and executes it during setup/installation, so it is an external dependency that can execute code.
- 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.