The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Node.js script located at skills/wp-project-triage/scripts/detect_wp_project.mjs to analyze the repository structure and classify the project kind.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted repository data used for classification and routing decisions.
Ingestion points: The triage process reads data from various project files including composer.json, package.json, style.css, block.json, and theme.json in the repository root and wp-content/ directory.
Boundary markers: No specific boundary markers or instructions to ignore embedded malicious content are defined for the agent when processing these files.
Capability inventory: The skill executes Node.js triage scripts and delegates to other workflows that likely involve bash command execution and file modifications.
Sanitization: No sanitization or validation of the content read from the project files is described before it influences the agent's routing behavior.

wordpress-router