wordpress-router

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script (detect_wp_project.mjs) to analyze project structure and identifies available tooling. It further recommends executing standard development commands (lint, test, build) found within the project configuration.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it bases its routing and command recommendations on the contents of untrusted files within the analyzed repository.
  • Ingestion points: Reads configuration files such as package.json, composer.json, theme.json, and block.json from the repository root.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are documented for isolating file content from the agent's logic.
  • Capability inventory: The skill performs filesystem triage and recommends shell command execution based on discovered scripts.
  • Sanitization: No explicit sanitization or validation of extracted script names or project metadata is mentioned before they are used in the decision-making process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 03:43 PM