lyxy-runner-javascript

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the official website for the Bun runtime (bun.sh) for installation purposes. This is a well-known and established service.
  • [REMOTE_CODE_EXECUTION]: The instructions include specific shell commands for installing Bun, such as curl -fsSL https://bun.sh/install | bash. The skill explicitly includes a safety constraint directing the agent to stop and wait for the user to perform the installation manually rather than executing it automatically.
  • [DYNAMIC_EXECUTION]: The primary purpose of the skill is to facilitate the execution of JavaScript and TypeScript code at runtime via the bun command.
  • [INDIRECT_PROMPT_INJECTION]: As the skill executes scripts that may be provided by the user or found in a project environment, it possesses an attack surface for indirect prompt injection.
  • Ingestion points: Script files processed by the bun <script_path> command.
  • Boundary markers: None explicitly defined in the skill instructions.
  • Capability inventory: Full script execution capabilities provided by the Bun runtime, including file system and network access.
  • Sanitization: The skill does not implement sanitization or validation of the scripts before execution, relying on the user to provide safe code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 04:20 AM
Security Audit — agent-trust-hub — lyxy-runner-javascript