laravel-11-12-app-guidelines
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the use of command-line tools like
php artisanandvendor/bin/pint, and thetinkerMCP tool for running arbitrary PHP code. These capabilities are expected for the task but represent a high level of system access. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it directs the agent to follow instructions from external project files. * Ingestion points: Documentation files (AGENTS.md, docs/README.md) and configuration files. * Boundary markers: None; the agent is not told to ignore instructions in these files. * Capability inventory: Access to CLI commands and arbitrary code execution via tinker. * Sanitization: No sanitization of the file content is performed.
Audit Metadata