Skills
skills/skills-shell/skills/ai-image-generation/Gen Agent Trust Hub

ai-image-generation

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the belt CLI tool and supplementary skills from the inference-sh GitHub organization and the inference.sh domain.
  • [COMMAND_EXECUTION]: The belt command is utilized for generating images and managing user authentication (belt login) on the inference.sh platform.
  • [DATA_EXFILTRATION]: User-provided prompts and image URLs are transmitted to the external inference.sh API for remote processing and image generation.
  • [PROMPT_INJECTION]: The skill processes user-supplied prompts within CLI command templates, which could be leveraged for indirect prompt injection.
  • Ingestion points: Prompt values within the --input JSON payload for the belt command in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided templates.
  • Capability inventory: The skill executes the belt command via the Bash tool.
  • Sanitization: No input validation or sanitization logic is documented within the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:03 PM