schema-markup

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, command execution, or unauthorized network operations were detected. The skill primarily consists of instructional content and JSON-LD examples.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided site information and external context files (e.g., .agents/product-marketing-context.md) to generate structured data. This constitutes a potential attack surface, though the risk is minimized by the skill's adherence to the rigid schema.org JSON-LD format.
  • Ingestion points: The skill reads .agents/product-marketing-context.md and processes user descriptions of web pages.
  • Boundary markers: No explicit delimiters are defined to separate untrusted context from instructions.
  • Capability inventory: The skill does not define any subprocess calls, network requests, or file writes; it only generates code blocks for the user.
  • Sanitization: The instructions emphasize validation using the Google Rich Results Test and Schema.org Validator.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 06:53 PM
Security Audit — agent-trust-hub — schema-markup