The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of local commands like composer run and vendor/bin/phpstan to perform static analysis.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it parses project-controlled configuration files to determine which commands the agent should execute.
Ingestion points: Project files composer.json, phpstan.neon, and phpstan.neon.dist are read by the scripts/phpstan_inspect.mjs script.
Boundary markers: No delimiters or isolation instructions are used to process these external inputs.
Capability inventory: The skill possesses the capability to execute shell commands and modify local files.
Sanitization: The skill does not validate or sanitize the content of the scripts or configuration parameters discovered in the analyzed repository.

wp-phpstan