book-cover-design
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an external installation script located at
https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.mdto set up the necessary CLI tool. - [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for processing user-supplied input through AI image generation prompts.
- Ingestion points: User-defined strings passed as the
promptvalue in thebelt app runcommand withinSKILL.md. - Boundary markers: The skill uses structured JSON payloads via the
--inputflag to delimit user data from the command execution. - Capability inventory: The skill utilizes the
beltCLI tool (restricted byallowed-tools) for image generation, editing, and upscaling. - Sanitization: No explicit sanitization or filtering of prompt content is defined in the skill instructions, as the output is restricted to image generation.
Audit Metadata