wp-json-schema-api

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for processing JSON schemas, which are structured data formats that typically ingest untrusted content from external sources or client requests.
  • Ingestion points: External data enters the processing pipeline via the $schema PHP variable as described in the code examples in SKILL.md and the normalization probes in references/profiles-and-normalization.md.
  • Boundary markers: The documentation explicitly advocates for a boundary between the 'server schema' (internal) and the 'prepared schema' (public), ensuring that internal constraints do not unintentionally leak or get overridden by external input.
  • Capability inventory: The skill utilizes standard WordPress core PHP functions to recursively traverse, filter, and modify data structures in the execution environment.
  • Sanitization: The skill demonstrates high-quality sanitization practices by instructing the automatic removal of internal sanitize_callback callables and other WordPress-specific metadata before a schema is transported, and it warns that preparation should not be trusted as a substitute for server-side validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 07:07 PM
Security Audit — agent-trust-hub — wp-json-schema-api