NYC

wordpress-router

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill executes a local Node.js triage script (node skills/wp-project-triage/scripts/detect_wp_project.mjs). This is an internal component of the skill set used to identify project structures.
  • [DYNAMIC_EXECUTION] (LOW): The skill instructions suggest running lint, test, and build commands found within the target repository. While standard for developer tools, this means the agent may execute arbitrary scripts defined in a repository's package.json or composer.json if directed.
  • [INDIRECT_PROMPT_INJECTION] (LOW):
  • Ingestion points: The triage process reads content from package.json, composer.json, style.css, and theme.json to determine project type.
  • Boundary markers: No specific boundary markers or instruction-ignoring delimiters are mentioned for the data ingested from these files.
  • Capability inventory: The skill can execute bash commands, node scripts, and WP-CLI commands based on the classification.
  • Sanitization: No explicit sanitization or validation of the strings read from the project files is documented before they are used to influence routing decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 06:37 PM