nvidia-kaggle-skill

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

• Third-party content exposure detected (high risk: 0.75). High likelihood: the required “Research Brief” workflow chains Kaggle research scripts that fetch outsider-authored free text (e.g., Kaggle discussion bodies/comments and kernel markdown/code) from Kaggle at runtime and then the agent uses that gathered text to write the brief, which becomes part of the LLM context.