ai-product-photography

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches installation guidelines and documentation from the inference-sh GitHub repository.
  • [COMMAND_EXECUTION]: Executes shell commands via the belt CLI tool to interact with the inference platform for image generation and processing.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to generate image prompts, which creates a potential surface for indirect prompt injection.
  • Ingestion points: User input is interpolated into the --input argument of belt app run commands within shell scripts and documentation examples.
  • Boundary markers: User prompts are encapsulated within JSON strings passed to the CLI.
  • Capability inventory: The skill utilizes the Bash tool, restricted to commands starting with belt.
  • Sanitization: No explicit sanitization or filtering of prompt text is performed before it is passed to the underlying AI models.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — ai-product-photography