mastering-pytorch-rl-nlp

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

• Third-party content exposure detected (high risk: 0.80). The skill's core documentation (SKILL.md and references like references/nlp-transformers.md and references/advanced-topics.md) explicitly shows workflows that load public third-party models and datasets (e.g., transformers.from_pretrained, pipeline() defaults, and datasets.load_dataset("wikipedia")) which ingest untrusted user-generated web content that the agent would read and use in its workflow.