Skills
skills/inference-sh-skills/skills/case-study-writing/Gen Agent Trust Hub

case-study-writing

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the vendor's belt CLI to run applications for web research (Tavily and Exa) and Python code execution. This behavior is restricted via the allowed-tools frontmatter to the belt command space.
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the belt-sh/cli and add related skills from the inference-sh registry. These are official resources belonging to the skill's author.
  • [SAFE]: The Python execution example provided for generating charts is a static script using Matplotlib. It saves a local image file and does not attempt to access sensitive credentials or perform unauthorized network operations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:28 AM