competitor-teardown

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of the infsh command-line tool to interact with various applications (search assistants, browsers, and data processing tools). These commands are restricted via the allowed-tools frontmatter configuration.
  • [EXTERNAL_DOWNLOADS]: Provides a link to installation instructions and scripts hosted on GitHub under the inference-sh organization. This repository is associated with the skill's author and platform.
  • [REMOTE_CODE_EXECUTION]: Contains a Python script designed to be executed via a dedicated application (infsh/python-executor). The script is used for generating data visualizations (positioning maps) and does not exhibit malicious patterns like network exfiltration or unauthorized file access.
  • [SAFE]: The skill uses established third-party services for web search and data extraction (e.g., Tavily, Exa), which are standard for research-oriented AI skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:25 PM
Security Audit — agent-trust-hub — competitor-teardown