scribe

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions include the installation of the knuckleswtf/scribe package via Composer. This is the official and standard tool for Scribe documentation generation in Laravel.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute commands like composer require, php artisan vendor:publish, and php artisan scribe:generate. These are standard operations for the tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and process Laravel source code (controllers, form requests, models) to extract documentation. This involves a data ingestion surface where external code influences the agent's output.
  • Ingestion points: Laravel PHP source files (controllers, requests, models).
  • Boundary markers: None explicitly defined in the instructions for parsing source code.
  • Capability inventory: The skill utilizes Read, Write, Glob, Grep, and Bash tools.
  • Sanitization: The skill relies on the agent's underlying safety filters and the standard Scribe parsing logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:11 AM
Security Audit — agent-trust-hub — scribe