ptq
Use when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AWQ", "quantize LLM", "quantize MoE", "quantize VLM", or needs to produce a quantized HuggingFace checkpoint from a pretrained model using ModelOpt. Do NOT use for multi-candidate recipe exploration or optimization (use quant-recipe-search).
72
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
Documentation is generally operational/benign, but it explicitly advises loading and executing model-provided Python via --trust_remote_code (direct RCE/backdoor vector) and documents an unquoted EXTRA_PIP_DEPS pattern in the launcher that can enable shell injection if attacker-controlled inputs are used; no explicit data-exfiltration or credential-theft code is present.
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
The required PTQ workflow can load outsider-authored model artifacts (e.g., when using unlisted models and `trust_remote_code`, it reads `modeling_*.py` and other repository files from the downloaded HF checkpoint via `hf_ptq.py`), which are free-form text and may include prompt-injection payloads; references to README/support tables are excluded as bundled material.
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 skill includes runtime commands that fetch and import remote executables/images (enroot import docker://nvcr.io#nvidia/tensorrt-llm/release:<version> and a git clone of https://github.com/huggingface/transformers.git) which pull and install remote code used during PTQ runs, so these are runtime external dependencies that execute remote code.
- Repository
- NVIDIA/Model-Optimizer
- Commit
33d05b0
- 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.