gpt-image

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the 'belt' CLI and related skills from the 'inference-sh' organization via npx.
  • [COMMAND_EXECUTION]: Uses the 'belt' CLI tool within a Bash environment to perform image generation and editing tasks as specified in the allowed-tools configuration.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text prompts which are passed to the 'belt' CLI. Ingestion points: 'prompt' parameter in SKILL.md. Boundary markers: JSON structure used in the CLI input. Capability inventory: Bash command execution via 'belt'. Sanitization: Not explicitly implemented in the skill code, relies on the underlying platform's shell execution safety and the CLI's internal validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 11:00 PM
Security Audit — agent-trust-hub — gpt-image