competitor-teardown

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the belt CLI tool to execute remote operations. These include running specialized agents for web searching (tavily/search-assistant, exa/search), extracting content from URLs (tavily/extract), and capturing website screenshots (infsh/agent-browser). While these commands interact with external services, they are the primary intended function of the skill for market research.
  • [EXTERNAL_DOWNLOADS]: The documentation includes instructions for users to install the belt CLI via npx skills add and points to a setup script hosted on GitHub (raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md). These are documented setup steps for the required tooling.
  • [DYNAMIC_EXECUTION]: The skill provides a template for generating visual positioning maps using Python (infsh/python-executor). The code uses standard libraries (matplotlib) to generate a static image based on hardcoded competitor data. This is a local visualization utility and does not process untrusted external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — competitor-teardown