gpt-image

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and installation scripts hosted on GitHub (inference-sh organization) and the inference.sh domain. These references are used for setting up the required CLI environment.
  • [COMMAND_EXECUTION]: The skill utilizes the belt command-line utility via a restricted Bash environment (allowed-tools: Bash(belt *)) to run image generation tasks. This prevents the execution of unauthorized shell commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface by accepting untrusted user data (prompts and image URLs) that are processed by the underlying AI model.
  • Ingestion points: User-supplied prompt, images, and mask fields in SKILL.md.
  • Boundary markers: Data is passed as structured JSON via the --input flag to the CLI tool.
  • Capability inventory: Command execution is limited to the belt tool; no file writing or broad network access is granted to the skill itself.
  • Sanitization: Input is wrapped in single quotes for the shell command, mitigating basic command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — gpt-image