json-schema-design

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external JSON data and schemas for validation tasks, which creates a potential surface for indirect prompt injection. * Ingestion points: The skill triggers on files with the *.schema.json extension and user requests for data validation. * Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed data or schemas. * Capability inventory: The Python utility provided in SKILL.md accesses the local file system using the Path.read_text method to load schema definitions. * Sanitization: No input validation, filtering, or sanitization is performed on the external JSON content or schema paths before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:22 PM