ai-image-generation

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation guides the user to install an external command-line tool using npx skills add belt-sh/cli and references installation guidelines hosted on GitHub (raw.githubusercontent.com/inference-sh/skills). These downloads are directed toward the service provider's official repositories and are necessary for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests user-provided text to generate images via external AI models.
  • Ingestion points: User-controlled prompts are passed as arguments to the belt CLI tool in SKILL.md examples.
  • Boundary markers: No explicit delimiters or boundary markers are defined in the command examples to isolate the prompt from the command structure.
  • Capability inventory: The skill utilizes the Bash tool to execute belt CLI commands.
  • Sanitization: The instructions do not specify sanitization methods; security is dependent on the backend AI models and the CLI tool's internal filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:21 PM
Security Audit — agent-trust-hub — ai-image-generation