The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the agent to run numerous shell commands, including ls, cat, find, grep, and php artisan route:list, to map out the application's structure and logic.
[PROMPT_INJECTION]: The skill is highly susceptible to indirect prompt injection due to its broad ingestion of untrusted data. \n
Ingestion points: Processes contents of all PHP files across directories like app/, database/, config/, and routes/ (Phase 1: Deep Discovery). \n
Boundary markers: No delimiters or safety instructions are provided to prevent the agent from obeying malicious instructions embedded in comments or strings within the analyzed codebase. \n
Capability inventory: The agent possesses the capability to execute shell commands and write to the filesystem. \n
Sanitization: No sanitization or validation logic is applied to the content read from the repository.
[DATA_EXFILTRATION]: Accesses sensitive application configuration files, including config/auth.php, config/permission.php, and config/cashier.php. It also reads database migrations and seeders which may expose security policies, billing logic, and sensitive test data.

test-plan