skills/automattic/agent-skills/wpds/Gen Agent Trust Hub

wpds

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a standard configuration for providing developer assistance related to the WordPress Design System (WPDS).
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data through a specialized MCP server (wpds:// protocol). While ingesting external data provides a theoretical surface for indirect prompt injection, in this context, it serves to ground the agent in authoritative design documentation, which is a best practice for accuracy.
  • [COMMAND_EXECUTION]: The skill instructs the agent to utilize local lint scripts for validating code snippets. This is a standard and expected behavior for developer-oriented AI agents and relies on the user's existing project configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:49 PM
Security Audit — agent-trust-hub — wpds