The Agent Skills Directory

[PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill analyzes untrusted repository files to determine workflow routing.
Ingestion points: composer.json, package.json, style.css, block.json, theme.json, and wp-content/ directory.
Boundary markers: Absent. The skill does not define specific delimiters to prevent the agent from following instructions embedded in these project files.
Capability inventory: Execution of a Node.js script (detect_wp_project.mjs) and delegation to other domain-specific skills.
Sanitization: No sanitization or content validation is mentioned for the parsed files.
[COMMAND_EXECUTION] (SAFE): Local script execution. The procedure executes node skills/wp-project-triage/scripts/detect_wp_project.mjs. This is a call to a local script within the agent's own skill directory and is considered standard operational behavior.

wordpress-router