torchforge-rl-training

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires ingesting public third‑party datasets (e.g., dataset.path: "openai/gsm8k", streaming: true) and fetching models from the HuggingFace Hub as part of its training workflow, so untrusted external content is read and can materially influence model behavior.