semantic-html

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is entirely instructional, providing a guide for developers to use the Builderius platform effectively. It does not contain any executable scripts, network calls, or attempts to access restricted file paths.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing external data through Builderius 'Collection' modules. It provides clear instructions on using boundary markers, specifically distinguishing between HTML-escaped content ({{field}}) and unescaped content ({{{field}}}). This serves to minimize the risk of cross-site scripting (XSS) when handling dynamic data. 1. Ingestion points: Collection and Template modules using data-b-context as described in SKILL.md. 2. Boundary markers: The skill documents the use of double vs. triple curly braces to control escaping. 3. Capability inventory: The skill facilitates the generation of HTML and SVG structures but does not include shell execution or file-system writing capabilities. 4. Sanitization: The skill identifies the platform's built-in escaping mechanism as the primary method for sanitizing external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — semantic-html