bricks-layouts
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a JSON schema for WordPress Bricks Builder templates that explicitly supports raw HTML content and arbitrary JavaScript execution via the
codeelement (javascriptCode,executeCode). This represents a significant attack surface: if an agent uses this skill to generate layout JSON based on untrusted data from a user or external source, it could be manipulated into producing a malicious payload that executes Cross-Site Scripting (XSS) or server-side code when the template is imported into a destination WordPress site. - Ingestion points: Data provided to the agent to populate the
textelement settings and thecodeelement'sjavascriptCodeproperty inSKILL.md. - Boundary markers: The skill lacks any instructions or delimiters to warn the agent against executing or including instructions found within the data it is processing.
- Capability inventory: The generated output is a template designed to be imported into a web building environment (WordPress Bricks), which possesses the capability to render HTML and execute the provided JavaScript.
- Sanitization: There are no sanitization, escaping, or validation requirements mentioned in the instructions to protect against malicious content interpolation.
Audit Metadata