schema-markup
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is instructional and follows security best practices by requiring validation of output and limiting the scope to visible page content. It explicitly prohibits misrepresenting content or adding deceptive markup.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external webpage content to generate JSON-LD markup, which creates a potential surface for indirect prompt injection if the source content contains malicious instructions. The skill mitigates this risk by instructing the agent to align strictly with visible content and prevent misleading or spammy markup.
- Ingestion points: Webpage content provided as input by the user or agent.
- Boundary markers: None specified for the input data stream.
- Capability inventory: The skill generates JSON-LD data blocks; it does not have autonomous file-system write or network execution capabilities.
- Sanitization: Explicit instructions are provided to filter out non-visible content and to validate all output against Schema.org and Google Rich Results standards.
Audit Metadata