product-photography

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install the belt CLI utility and references documentation and setup scripts hosted on the inference-sh GitHub repository. These are legitimate resources for the skill's stated purpose of using the inference.sh platform.- [COMMAND_EXECUTION]: The skill demonstrates the use of the belt command-line tool to execute various AI image generation models (such as bytedance/seedream-4-5 and falai/flux-dev-lora). The tool usage is consistent with the skill's description and is restricted to the belt namespace.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined natural language prompts to guide the behavior of image generation models. While this represents a data ingestion surface, the impact is confined to the content of the generated image and does not involve high-risk capabilities such as file system modifications or data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — product-photography