validating-json-data
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and implementation examples for the
z-schemalibrary, a reputable and widely-used JSON Schema validator. The content follows standard development practices and is educational in nature. - [EXTERNAL_DOWNLOADS]: The skill references the
z-schemalibrary from the official npm registry, which is a trusted source for JavaScript dependencies. - [PROMPT_INJECTION]: The skill describes processing external JSON data and schemas, which creates a surface for indirect prompt injection. This risk is inherent to the skill's primary purpose of validation and is addressed through the library's validation logic.
- Ingestion points:
validator.validate()andvalidator.validateSchema()methods inSKILL.mdprocess user-supplied JSON data and schema definitions. - Boundary markers: No explicit markers or specific warnings against embedded instructions are present in the provided documentation snippets.
- Capability inventory: The skill demonstrates using file system access (
fs.readFileSync) for resolving local schemas and network capabilities for resolving remote references. - Sanitization: The library performs structure and type validation against the schema, which provides the primary sanitization mechanism for the ingested data.
Audit Metadata