unopim-setup

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of development dependencies including the laravel/boost Composer package and the @playwright/mcp Node package. These tools are sourced from well-known repositories and registries.
  • [COMMAND_EXECUTION]: The skill instructs the agent to run local environment scripts (doctor.sh, install-hooks.sh) and standard PHP/Composer commands to configure the workspace. These actions are performed within the project context provided by the vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface where the agent ingests application-level data to assist in development tasks. 1. Ingestion points: Application logs, database schemas, and documentation retrieved via the Boost MCP server. 2. Boundary markers: None defined in the setup instructions. 3. Capability inventory: Shell execution for environment checks and dependency management, and database introspection capabilities. 4. Sanitization: No specific data sanitization or filtering is described in the setup process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 09:39 AM