NYC

wp-plugin-development

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Prompt Injection] (HIGH): The skill is highly vulnerable to Indirect Prompt Injection (Category 8). It processes untrusted external content (WordPress plugin source code) and possesses capabilities to modify files and execute commands.
  • Ingestion points: Plugin main files, header metadata, and repository structures (e.g., wp-content/plugins/) via detect_plugins.mjs.
  • Boundary markers: No boundary markers or 'ignore' instructions are present to prevent the agent from following prompts embedded in the plugin code.
  • Capability inventory: Includes filesystem write access for refactoring, execution of node scripts, bash commands, and WP-CLI which can interact with the database and environment.
  • Sanitization: No sanitization or escaping of ingested source code is specified before the agent processes it.
  • [Command Execution] (LOW): The skill executes local Node.js scripts as part of its triage and detection workflow.
  • Evidence: Execution of node skills/wp-project-triage/scripts/detect_wp_project.mjs and node skills/wp-plugin-development/scripts/detect_plugins.mjs. While these appear to be internal, local script execution is a sensitive capability.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 11:00 AM