resource
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to drive code generation and command execution.
- Ingestion points: In
SKILL.md, the agent is instructed to gather requirements from the user, including "Model name", "Fields to include", "Relationships to manage", and "Custom actions". - Boundary markers: No boundary markers or "ignore embedded instructions" warnings are present to handle potentially malicious user input.
- Capability inventory: The skill utilizes shell command execution (
php artisan) and file system write operations (app/Filament/Resources/...). - Sanitization: There are no instructions to sanitize or validate the user-provided strings before they are used as arguments in shell commands or written into PHP files.
- [COMMAND_EXECUTION]: The skill provides templates for executing local shell commands.
- Evidence:
SKILL.mdcontains multiple examples of shell commands such asphp artisan make:filament-resource ModelNameandphp artisan make:filament-relation-manager ResourceName RelationName column_name. These commands directly interpolate user-supplied requirements as arguments.
Audit Metadata