laravel-11-12-app-guidelines

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it instructs the agent to prioritize and follow instructions from external, potentially untrusted repository files.
  • Ingestion points: The skill explicitly directs the agent to read AGENTS.md, docs/README.md, and relevant module documentation to guide its behavior.
  • Boundary markers: No clear delimiters or instructions are provided to the agent to ignore embedded instructions within these data files.
  • Capability inventory: The agent is granted access to high-privilege capabilities, including tinker (arbitrary PHP execution), database-query (SQL access), and list-artisan-commands (Artisan command execution).
  • Sanitization: No sanitization or validation logic is specified for the content processed from the repository files.
  • [COMMAND_EXECUTION]: The skill guidelines instruct the agent to run various command-line interface (CLI) tools, including PHPUnit for testing, Laravel Pint for code styling, and various php artisan commands. These are standard operations for the intended Laravel development workflow.
  • [NO_CODE]: This skill is composed exclusively of Markdown documentation files (SKILL.md and references/boost-tools.md) and does not bundle any executable scripts or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 09:31 PM