hqq-quantization

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill's examples explicitly load models, tokenizers, and datasets from public hubs (e.g., AutoModelForCausalLM.from_pretrained("mobiuslabsgmbh/...") and AutoTokenizer.from_pretrained("meta-llama/..."), load_dataset("wikitext"), and links to the HuggingFace/GitHub repos), which are open, user-provided third-party resources that the agent is expected to load and interpret as part of its workflow.