megatron-memory-estimator

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

• Third-party content exposure detected (high risk: 0.90). This skill's primary workflow (scripts/estimate_from_hf.py) explicitly fetches and parses HuggingFace model paths/configs (e.g., deepseek-ai/DeepSeek-V3, Qwen/...) from the public HuggingFace model hub, meaning it ingests untrusted, user-provided third-party content as part of its operation and could therefore enable indirect prompt injection.