competitor-teardown

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the belt-sh/cli tool and add supplementary skills from the inference-sh organization. These resources are necessary for the skill to function as intended within its target platform.
  • [COMMAND_EXECUTION]: The skill uses the belt CLI to run several automated tasks, including market research queries via Tavily and Exa, and website screenshotting via a headless browser agent. Access is restricted to the belt tool via the allowed-tools configuration in the frontmatter.
  • [COMMAND_EXECUTION]: Includes a Python script template used to generate a 2x2 competitive positioning map with the matplotlib library. This script is intended to be executed through the platform's Python executor tool.
  • [PROMPT_INJECTION]: By design, the skill processes information from external websites and search results to build reports. This creates an interface for indirect prompt injection if those external sources contain malicious instructions, though this is a standard risk for research-oriented skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:15 AM
Security Audit — agent-trust-hub — competitor-teardown