Skills
Navigate
skills/inference-sh/skills/image-upscaling/Gen Agent Trust Hub

image-upscaling

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the belt CLI via npx skills add belt-sh/cli and links to installation documentation on the official inference-sh GitHub repository. These resources are provided by the skill's author and represent standard setup procedures for the platform.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI to run image processing applications on the inference.sh platform, such as real-esrgan and topaz-image-upscaler.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of data from untrusted external sources.
  • Ingestion points: External image URLs passed to the belt app run command via the --input parameter (documented in SKILL.md).
  • Boundary markers: None identified in the documentation to delimit external input from instructions.
  • Capability inventory: Executes CLI commands through the belt tool (documented in SKILL.md).
  • Sanitization: None identified; external URLs are passed directly to the application runner.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:13 PM
Security Audit — agent-trust-hub — image-upscaling