The Agent Skills Directory

[SAFE]: The skill serves as a security guide and audit tool for Laravel 13, promoting best practices such as rate limiting, prepared statements, and mass assignment protection. It includes educational examples of insecure code to illustrate what to avoid.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to audit local codebases using tools like Grep and Read. This functionality requires the agent to ingest untrusted content from the files it analyzes, which is an inherent part of a security auditing tool.
Ingestion points: PHP source files and environment configuration files read during the audit process specified in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the code being audited.
Capability inventory: The skill utilizes Read, Write, Glob, Grep, and Bash tools to perform its auditing and hardening tasks.
Sanitization: The provided instructions do not specify sanitization or filtering of the content being audited.

laravel-security