character-design-sheet
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
beltCLI tool via theBashtool to perform image generation and processing tasks. This is the primary function of the skill and aligns with its stated purpose of character design. - [INDIRECT_PROMPT_INJECTION]: The skill contains a vulnerability surface where user-provided prompts are interpolated into CLI command arguments.
- Ingestion points: Prompts are placed within JSON structures in
SKILL.md(e.g.,belt app runblocks). - Boundary markers: Prompts are delimited by double quotes within JSON objects.
- Capability inventory: The skill has access to the
Bashtool to executebeltCLI commands. - Sanitization: No explicit sanitization or filtering is described in the prompt construction.
- [EXTERNAL_DOWNLOADS]: The skill references installation instructions for the
beltCLI located athttps://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md. This is a reference to the service provider's official documentation.
Audit Metadata