Skills
skills/qu-skills/skills/image-upscaling/Gen Agent Trust Hub

image-upscaling

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation documentation from the inference-sh organization's public GitHub repository to set up the belt CLI tool.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI to interact with the inference.sh API, with tool access restricted to this specific command set via the allowed-tools configuration.
  • [PROMPT_INJECTION]: The skill ingests untrusted data through image URLs and generation prompts in SKILL.md. While it lacks explicit boundary markers, the execution scope is limited to the belt CLI, which is consistent with the primary purpose of image processing integrations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 10:49 PM
Security Audit — agent-trust-hub — image-upscaling