competitor-teardown

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides links to fetch CLI installation guidelines from the vendor's official GitHub repository (raw.githubusercontent.com/inference-sh/*). These are neutral references for tool setup.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI tool to execute various research tasks, such as web searches via Tavily and Exa, and automated browser actions for taking screenshots. These operations are aligned with the skill's stated purpose of market research.
  • [DYNAMIC_EXECUTION]: The skill includes a Python script for generating positioning maps using matplotlib. While this involves runtime code execution via infsh/python-executor, the code is a static template for data visualization and does not process untrusted external inputs in a dangerous manner.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:22 PM
Security Audit — agent-trust-hub — competitor-teardown