schema-markup
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (
scripts/schema_validator.py) to perform audits on HTML files. This is a primary function of the tool but involves executing local code based on user-provided files. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting untrusted data (HTML) from external sources during the audit process. * Ingestion points: HTML content or URLs provided for analysis in 'Mode 1: Audit Existing Markup'. * Boundary markers: No delimiters or specific warnings to ignore embedded instructions in the processed HTML are provided. * Capability inventory: The skill can execute local scripts and generate JSON-LD script blocks. * Sanitization: No sanitization or validation of the input HTML content is mentioned prior to processing.
Audit Metadata