uv-mamba-architecture

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Workflow 2 in SKILL.md) explicitly loads pretrained models and tokenizers from the public HuggingFace hub using from_pretrained (e.g., "state-spaces/mamba-2.8b" and "EleutherAI/gpt-neox-20b"), which are open third‑party artifacts that the agent fetches at runtime and that can materially change its outputs and behavior.