wp-ai-client

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides comprehensive security guidance for WordPress AI integrations, explicitly instructing developers to sanitize all user-provided data using standard WordPress functions like sanitize_textarea_field and wp_unslash before including them in AI prompts.
  • [SAFE]: It emphasizes the importance of treating AI-generated content as untrusted input, requiring validation and escaping before storage or rendering.
  • [SAFE]: The documentation includes strict rules for tool usage (WordPress Abilities), recommending a granular allowlist approach via WP_AI_Client_Ability_Function_Resolver to prevent unauthorized function execution by models.
  • [SAFE]: Credential security is addressed by forbidding hard-coded API keys and directing developers to use official WordPress Connectors or environment variables.
  • [EXTERNAL_DOWNLOADS]: The skill references technical documentation and field guides from make.wordpress.org. These are official, well-known, and trusted resources for WordPress core development and do not represent a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:07 PM
Security Audit — agent-trust-hub — wp-ai-client