competitor-teardown

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an installation script from raw.githubusercontent.com/inference-sh/, which is consistent with the vendor's identity ('skills-shell' using 'inference.sh' tools).
  • [COMMAND_EXECUTION]: The skill uses belt app run commands to execute various specialized tools (e.g., tavily/search-assistant, infsh/agent-browser, infsh/python-executor). These are part of the intended functionality for research and data processing.
  • [DATA_EXFILTRATION]: No evidence of sensitive data exfiltration was found. The network operations (via belt) are focused on gathering public market intelligence and screenshots of competitor websites.
  • [COMMAND_EXECUTION]: The skill includes a Python script executed via belt app run infsh/python-executor to generate a positioning map using matplotlib. The code is static, benign, and restricted to plotting and saving an image locally.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 10:16 AM