skills/acedatacloud/skills/wordpress/Gen Agent Trust Hub

wordpress

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute curl and jq. This is the intended and controlled method for interacting with the WordPress REST API.
  • [DATA_EXPOSURE]: Sensitive credentials (WordPress Application Password) are correctly handled through environment variables provided by the platform's connection. The skill includes explicit instructions for the AI to never log or echo these secrets, adhering to best practices for credential handling.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data for use in post titles and content. It mitigates injection risks by using jq --arg for safe parameterization, ensuring that user input is treated as data and not as executable shell commands or malformed JSON payloads.
  • [SAFE]: The implementation relies on standard command-line tools (curl, jq) and avoids remote script execution or unverifiable dependencies. All network requests are directed to the user-specified WordPress site URL.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 05:10 PM
Security Audit — agent-trust-hub — wordpress