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.md to 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 prompt value in the belt app run command within SKILL.md.
  • Boundary markers: The skill uses structured JSON payloads via the --input flag to delimit user data from the command execution.
  • Capability inventory: The skill utilizes the belt CLI tool (restricted by allowed-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
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:22 PM
Security Audit — agent-trust-hub — book-cover-design