The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface. It fetches ticket content, descriptions, and comments from external sources like GitHub, Linear, or local markdown files to determine its implementation steps.
Ingestion points: Processes external issue trackers and specification documents (referenced in Step 1 of SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the fetched ticket data.
Capability inventory: The agent can execute shell commands (git, composer), run PHP code (php artisan, pest), and modify the local filesystem.
Sanitization: No explicit sanitization or validation of the fetched ticket content is performed before it influences agent behavior.
[COMMAND_EXECUTION]: The skill uses several command-line tools to perform its tasks, including php artisan, composer, git, and PHP binaries (pint, pest, phpstan). These are standard tools for Laravel development, but they represent the execution of local system commands based on generated logic.
[DYNAMIC_EXECUTION]: The core loop of the skill involves writing PHP source code and tests, then executing them immediately via php artisan test or vendor/bin/pest. This runtime execution of locally generated code is the intended purpose of the skill but constitutes dynamic execution.

implement-plus