biome-linting
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The skill contains only instructional and configuration content related to code quality tools. No attempts to override agent behavior, bypass safety filters, or extract system prompts were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths (e.g., .ssh, .aws), or suspicious network operations were detected. Domain references are limited to legitimate project sites like biomejs.dev.
- [Unverifiable Dependencies] (LOW): The skill references '@biomejs/biome', a well-known open-source tool. While the agent is instructed to install this via npm, it is a standard dependency for the stated purpose. [TRUST-SCOPE-RULE] applies as the tool is widely recognized in the frontend ecosystem.
- [Indirect Prompt Injection] (LOW): The skill's purpose is to process external source code for linting. While this is an ingestion surface, the output is diagnostic (lint errors/formatting). No evidence of instructions being interpolated into an executable context was found.
- [Command Execution] (SAFE): The bash commands provided in the documentation (npm install, npx biome) are standard for the tool's operation and do not include suspicious piping to shells or execution of remote scripts.
Audit Metadata