The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill instructs the agent to run php artisan commands (e.g., make:filament-resource). These are standard Laravel development commands and are consistent with the skill's primary purpose.
[PROMPT_INJECTION] (SAFE): No instructions found that attempt to bypass AI safety guardrails or override system prompts.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill identifies user-provided requirements (Model names, field names) to generate code and commands. This presents a potential surface for indirect prompt injection if malicious data is provided, but it is mitigated by the standard nature of the generated code and the local execution context.
Ingestion points: Requirements gathering step (Model names, fields).
Boundary markers: Absent.
Capability inventory: Execution of php artisan commands and file writing to app/Filament.
Sanitization: Not explicitly defined in the skill instructions.
[DATA_EXFILTRATION] (SAFE): No evidence of sensitive file access or network operations. The skill references local absolute paths for documentation, but these do not facilitate data exfiltration.

filament-resource