biome

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using npm and npx to manage dependencies and run the Biome tool (e.g., npm i -D -E @biomejs/biome, npx @biomejs/biome init, npx @biomejs/biome check .). these commands are used as part of a standard development workflow for project configuration and code analysis.\n- [EXTERNAL_DOWNLOADS]: The skill installs the @biomejs/biome package from the npm registry. Biome is an established, open-source tool for formatting and linting frontend assets.\n- [PROMPT_INJECTION]: The skill processes content from local files like package.json, biome.json, and AGENTS.md, which creates a surface for indirect prompt injection if these files contain instructions designed to manipulate the agent's behavior.\n
  • Ingestion points: The files package.json, biome.json, and AGENTS.md are ingested to detect project state and configure the tool (found in SKILL.md).\n
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when processing these files.\n
  • Capability inventory: The skill can execute commands via npm/npx and modify repository files (found in SKILL.md).\n
  • Sanitization: No content validation or sanitization is specified for the data read from these files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 02:18 AM
Security Audit — agent-trust-hub — biome