Skills
Navigate
skills/anasadda/skills/logo-design-guide/Gen Agent Trust Hub

logo-design-guide

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches configuration and instructions from the inference-sh GitHub repository.
  • Evidence: Links to cli-install.md and npx skills add commands targeting the inference-sh namespace in SKILL.md.
  • [COMMAND_EXECUTION]: Uses the allowed belt CLI tool to perform image generation tasks.
  • Evidence: Multiple belt app run calls within SKILL.md for generating logo concepts and upscaling images.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that interpolates potentially untrusted user input into command parameters.
  • Ingestion points: User-provided prompts within the JSON --input for belt app run calls in SKILL.md.
  • Boundary markers: None.
  • Capability inventory: Subprocess execution of the belt CLI tool in SKILL.md.
  • Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 10:25 AM