wp-rest-api
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js triage script (
skills/wp-project-triage/scripts/detect_wp_project.mjs) to identify WordPress projects within the filesystem. This is a standard functional step for the intended development workflow. - [SAFE]: The skill promotes secure development practices, specifically emphasizing the use of
permission_callbackfor authorization and mandating JSON Schema-based validation and sanitization for all request arguments. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository files, which represents an attack surface for indirect prompt injection.
- Ingestion points: WordPress project files, including plugin and theme entrypoints (SKILL.md).
- Boundary markers: No specific delimiters or warnings for the agent are defined for the read operations.
- Capability inventory: The environment provides shell (bash) and Node.js execution capabilities (SKILL.md compatibility).
- Sanitization: No specific sanitization or validation of the ingested code content is performed prior to analysis.
Audit Metadata