evaluation
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "run nel". Handles deployment, config generation, and evaluation execution. Not for quantizing models (use ptq), deploying/serving models (use deployment), or comparing completed baseline-vs-quantized results (use compare-results).
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
SKILL.md:110-138 describes fetching and reading (outsider-authored) web sources such as recipes.vllm.ai pages and HuggingFace model cards at runtime, and those fetched free-text pages are then used to write LLM-relevant configuration, creating an indirect prompt-injection exposure path.
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
Flagged because the skill explicitly instructs fetching runtime content from recipes.vllm.ai/<org>/<model> to derive deployment/serve flags and shows an example pre_cmd that curls https://huggingface.co/.../reasoning_parser.py (downloadable code) which would be fetched/executed at runtime, so external content can directly control prompts/commands or execute code.
- Repository
- NVIDIA/Model-Optimizer
- Commit
87c9f8c
- 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.