skills/terminalskills/skills/bruno/Gen Agent Trust Hub

bruno

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the Bruno CLI tool (@usebruno/cli) from the official NPM registry and official desktop application installers via standard package managers like Homebrew, WinGet, and Flatpak.
  • [COMMAND_EXECUTION]: Includes standard CLI commands for installing, configuring, and executing API test collections using the bru command-line interface.
  • [DYNAMIC_EXECUTION]: Documents the capability to execute JavaScript scripts within Bruno collections for request signing and response assertions. The skill correctly identifies that scripts run in a restricted 'Safe Mode' by default and provides explicit security guidelines on when to use 'Developer Mode'.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing structured data from API collections, which involves the following components: 1. Ingestion points: Reads collection files (.yml, .bru) and environment configurations (.env, environments/*.yml) as specified in SKILL.md. 2. Boundary markers: Dynamic data is interpolated using standard {{variable}} delimiters. 3. Capability inventory: The skill uses the bru CLI to perform network operations and execute JavaScript logic within runtime script blocks. 4. Sanitization: The instructions recommend best practices such as using .gitignore for secrets and using 'Safe Mode' to restrict execution to bundled libraries.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 02:42 PM