roblox-build-and-env
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches Luau type definitions and toolchain components from public GitHub repositories.
- Evidence: Downloads
globalTypes.d.luaufrom theJohnnyMorganz/luau-lsprepository and references therojo-rbx/aftmanreleases page. - [COMMAND_EXECUTION]: Executes several package management and build tools to configure the local development environment.
- Evidence: Utilizes
npm install,aftman install,wally install, androjo buildto prepare the project artifacts. - [PROMPT_INJECTION]: The skill processes untrusted local configuration files which serves as a potential surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read
package.json,aftman.toml, andwally.tomlfrom the repository root to determine tool versions and dependencies (File: SKILL.md). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when reading these files.
- Capability inventory: The skill possesses extensive capabilities including network access via
curl, file system modification, and shell command execution through multiple package managers. - Sanitization: Content from configuration files is not validated or sanitized before being used to construct commands or drive agent logic.
Audit Metadata