timesfm-forecasting

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly downloads and loads third‑party content as part of its required workflow (SKILL.md states "TimesFM weights ... download on-demand from HuggingFace" and the examples/finetuning script fetches public datasets from autogluon.s3), so the agent ingests untrusted public resources (model checkpoints and datasets) that will directly influence model behavior and subsequent actions.