schema-markup
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The instructions are task-oriented and do not contain any patterns used to bypass AI safety filters or override system instructions.
- Data Exposure & Exfiltration (SAFE): No hardcoded credentials or access to sensitive system paths (like SSH keys or AWS configs) were found. The mention of
.claude/product-marketing-context.mdrefers to a local context file intended for the agent's use. - Remote Code Execution (SAFE): There are no commands that download or execute external scripts (e.g., curl | bash). All code examples are static JSON-LD templates.
- Unverifiable Dependencies (SAFE): The skill does not define any external package dependencies in standard formats like package.json or requirements.txt.
- Obfuscation (SAFE): All content is in plain markdown and JSON. No hidden characters, Base64 encoding, or homoglyphs were detected.
- Indirect Prompt Injection (LOW): The skill is designed to process user-provided website data to generate markup. While this is a data ingestion surface, the skill lacks the capabilities (like file system writes or network requests) that would make an injection attack exploitable.
Audit Metadata