hqq-quantization

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly fetches and uses public, user‑provided models and data (e.g., AutoModelForCausalLM.from_pretrained("mobiuslabsgmbh/...", loading HuggingFace models, and load_dataset("wikitext") plus links to HuggingFace/GitHub), so untrusted third‑party content is ingested and directly influences generation/decisions, creating a clear indirect prompt‑injection risk.