competitor-teardown

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: References installation instructions for the 'belt' CLI from the author's official GitHub repository.
  • [COMMAND_EXECUTION]: Utilizes the 'belt' CLI to interface with search and browsing tools (Tavily, Exa, Agent-Browser) for market research.
  • [DYNAMIC_EXECUTION]: Uses a Python executor to generate a positioning map visualization using matplotlib. The script is statically defined within the skill and focuses on data visualization.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Processes competitive data retrieved from external search engines (Tavily and Exa) into the agent's context.
  • Boundary markers: Uses standard markdown tables and SWOT templates; no specific escape delimiters are defined for the search data.
  • Capability inventory: The skill allows execution of CLI tools and execution of Python scripts via the 'belt' utility.
  • Sanitization: Relies on the underlying agent's standard handling of tool outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:28 AM
Security Audit — agent-trust-hub — competitor-teardown