Skills
Navigate
skills/nousresearch/hermes-agent/weights-and-biases/Gen Agent Trust Hub

weights-and-biases

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation and use of the wandb Python library, which is the official client for Weights & Biases, a well-known service for machine learning experiment tracking.\n- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates how to ingest external datasets and model files using the wandb.Artifact API.\n
  • Ingestion points: External data is brought into the environment via artifact.download() calls in SKILL.md and references/artifacts.md.\n
  • Boundary markers: The examples do not specify boundary markers or validation steps for the content of the downloaded artifacts.\n
  • Capability inventory: The skill includes capabilities for writing to the file system (torch.save, artifact.add_file) and performing network operations through the wandb logging and artifact management APIs.\n
  • Sanitization: There are no explicit sanitization or validation routines shown for the data loaded from external artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 04:02 PM