Skills
Navigate
skills/tabooharmony/roblox-brain/roblox-testing/Gen Agent Trust Hub

roblox-testing

Fail

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The file references/full.md contains a GitHub Actions workflow example that uses the command curl -LsSf https://raw.githubusercontent.com/nicbarker/aftman/main/install.sh | sh. This is a dangerous pattern that executes a remote script directly in the shell environment without any integrity verification or version pinning from a personal GitHub repository.
  • [EXTERNAL_DOWNLOADS]: The skill references and downloads content from external third-party sources that are not recognized as trusted organizations or well-known services. Specifically, it pulls patterns from https://raw.githubusercontent.com/brockmartin/roblox-game-skill/main/references/testing-patterns.md and recommends downloading the aftman tool from a personal repository.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute multiple shell commands, including selene, stylua, luau-lsp, and lune, which are used to process project source code.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 5, 2026, 09:04 PM
Security Audit — agent-trust-hub — roblox-testing