wordpress

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains examples that pass passwords/secrets directly on the command line and Docker env (e.g., --dbpass=secret, -e WORDPRESS_DB_PASSWORD=secret), which forces the agent to handle or emit secret values verbatim and creates an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.72). The required workflow includes calling the WordPress REST API (e.g., fetch(${WP_API}/posts...) / .../pages?...&acf) which ingests outsider-authored content from the WordPress site (posts/pages/ACF fields) into the agent’s LLM context via the fetched JSON/body text.