diffusers-cli

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • Remote Repository Code Execution: The --trust-remote-code parameter allows the skill to execute custom code from Hugging Face Hub repositories, which is required for certain model architectures but involves running external logic.
  • Remote Execution Environment: The skill can offload tasks to an external Hugging Face Sandbox via the --remote flag, which involves network data transfer and remote command invocation.
  • Dynamic Package Installation: Through the --dependencies flag, the skill can install arbitrary Python packages during remote execution to satisfy specific model requirements.
  • Credential Management: The tool retrieves the HF_TOKEN from the local environment and forwards it to the remote sandbox to facilitate access to restricted models.
  • External Content Loading: The CLI accepts URLs for media inputs (images, video, audio) in its arguments, fetching this data from the network before processing.
  • Indirect Instruction Processing: The skill ingests untrusted input. Ingestion points: pipeline-kwargs JSON and media URLs defined in run.md. Boundary markers: No explicit instruction delimiters are mentioned in the usage examples. Capability inventory: Includes shell command execution, remote code loading, package installation, and file system operations. Sanitization: Relies on JSON schema validation but does not explicitly filter natural language content within prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 09:44 AM
Security Audit — agent-trust-hub — diffusers-cli