character-design-sheet

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions and setup scripts hosted in the inference-sh/skills repository on GitHub.
  • [EXTERNAL_DOWNLOADS]: The instructions include commands to install external components from the belt-sh and inference-sh organizations using the npx skills add command.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where user-supplied character descriptions are interpolated into image generation prompts.
  • Ingestion points: Prompt strings within the --input parameter in SKILL.md.
  • Boundary markers: Input is structured as JSON objects.
  • Capability inventory: The skill is restricted to running the belt command via Bash.
  • Sanitization: User-supplied prompts are utilized directly by the generation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — character-design-sheet