skills/g1joshi/agent-skills/biome/Gen Agent Trust Hub

biome

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to execute @biomejs/biome via npx. This is the standard method for running the official Biome toolchain and targets a well-known, legitimate package registry.
  • [COMMAND_EXECUTION]: The skill includes several CLI commands for project initialization (biome init) and code verification (biome check, biome ci). These are standard development operations restricted to the local workspace.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a data ingestion surface through its core function of processing codebase files for linting and formatting. Evidence Chain:
  • Ingestion points: Source code files (JavaScript, TypeScript, JSX, JSON) processed by the tool.
  • Boundary markers: Not present in the provided instructions.
  • Capability inventory: Command execution via npx and local file system modification via the --write flag.
  • Sanitization: Not applicable to these standard CLI tool instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 03:36 AM