logo-design-guide

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill uses templates that interpolate text prompts into CLI command arguments for image generation. This represents a surface area for indirect prompt injection if user-provided content is placed into the prompt fields without proper sanitization.\n
  • Ingestion points: The 'prompt' field within the JSON input for the 'belt app run' command in SKILL.md.\n
  • Boundary markers: Absent.\n
  • Capability inventory: Execution of the 'belt' CLI via the Bash tool (restricted by allowed-tools).\n
  • Sanitization: No instructions or mechanisms for sanitizing or escaping user-provided text are present.\n- [EXTERNAL_DOWNLOADS]: The skill references an external installation guide for its primary CLI tool hosted on the vendor's GitHub repository.\n
  • Evidence: https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md\n- [COMMAND_EXECUTION]: The skill is designed to execute the 'belt' CLI tool for image generation, refining concepts, and upscaling images. The execution environment is scoped via the 'allowed-tools' frontmatter to only permit 'belt' commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:23 PM
Security Audit — agent-trust-hub — logo-design-guide