schema-markup
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze web page content to generate corresponding structured data. This represents a standard vulnerability surface where instructions could theoretically be embedded in analyzed data (e.g., HTML comments); however, the skill possesses no tools for code execution, file writing, or network operations, rendering this surface benign in the current implementation.
- [DATA_EXPOSURE]: The instructions direct the agent to check for and read a specific local context file (
.agents/product-marketing-context.md). This file is intended to provide specific marketing context for the agent's tasks and does not involve accessing sensitive system credentials, private keys, or standard environment variables.
Audit Metadata