hugging-face-community-evals

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow invokes inspect/lighteval to run evaluations for a user-specified --model (Hugging Face Hub) and --task/--tasks, which at runtime will cause the framework to ingest outsider-authored benchmark data/prompts associated with those tasks from the installed inspect-evals/task sources.