background-removal

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill is a well-structured wrapper for the 'belt' CLI tool, used to perform AI inference tasks. No malicious patterns such as credential harvesting, obfuscation, or persistence were detected.
  • [COMMAND_EXECUTION]: Utilizes the 'belt' command to execute image processing workflows on the inference.sh platform. The 'allowed-tools' metadata correctly restricts bash execution to this specific command, adhering to the principle of least privilege.
  • [EXTERNAL_DOWNLOADS]: References installation guides and configuration files located on the inference-sh GitHub organization and the official inference.sh domain. These are recognized as legitimate vendor resources for the stated functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data via 'image_url' and 'prompt' parameters in shell commands. While this presents a theoretical attack surface for indirect injection, the risk is mitigated by the use of structured JSON inputs and the specific nature of the image processing tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:40 PM
Security Audit — agent-trust-hub — background-removal