background-removal

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the 'belt' CLI tool using 'npx skills add belt-sh/cli'. It also references installation documentation hosted on GitHub by the 'inference-sh' organization.
  • [COMMAND_EXECUTION]: The documentation provides multiple examples of executing shell commands using the 'belt' CLI to login and run AI models (e.g., 'belt app run infsh/birefnet'). These are standard operations for the intended use case of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data via the 'image_url' parameter.
  • Ingestion points: The 'image_url' value provided to the 'belt app run' command in SKILL.md.
  • Boundary markers: None present in the example command snippets.
  • Capability inventory: The skill uses 'Bash' to execute the 'belt' command, which performs network operations to send the image to the inference service.
  • Sanitization: Input sanitization is expected to be handled by the 'belt' CLI tool and the backend API it communicates with.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 10:59 PM
Security Audit — agent-trust-hub — background-removal