ray-train

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates how to ingest external datasets into training pipelines, specifically through the train_dataset parameter in the HuggingFace Transformers workflow. This establishes a vulnerability surface where adversarial instructions within the training data could be executed or influence the training process.\n
  • Ingestion points: The train_dataset variable in the TransformersTrainer example in SKILL.md.\n
  • Boundary markers: No delimiters or 'ignore embedded instructions' warnings are included in the code examples to separate data from execution logic.\n
  • Capability inventory: The training process involves distributed task execution on Ray nodes, file system persistence for checkpoints (torch.save), and inter-node network communication.\n
  • Sanitization: The provided workflows do not demonstrate validation, filtering, or sanitization of input data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:08 PM
Security Audit — agent-trust-hub — ray-train