wp-rest-api

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the user's repository (WordPress source code) to triage and modify REST API endpoints.
  • Ingestion points: The skill reads PHP files from the target plugin/theme/mu-plugin entrypoints to locate REST usage.
  • Boundary markers: The instructions do not specify boundary markers or delimiters to prevent the agent from interpreting code comments or string literals as instructions.
  • Capability inventory: The skill possesses filesystem write capabilities to create or update REST routes and can execute shell commands for triage and searching.
  • Sanitization: There is no evidence of sanitization or filtering of the ingested source code content prior to its processing by the agent.
  • [COMMAND_EXECUTION]: The skill executes a triage script located at skills/wp-project-triage/scripts/detect_wp_project.mjs. This script is part of the vendor's environment but represents the execution of logic external to this specific skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:51 PM
Security Audit — agent-trust-hub — wp-rest-api