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
$schemaPHP variable as described in the code examples inSKILL.mdand the normalization probes inreferences/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_callbackcallables 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