NYC

wp-playground

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill uses npx @wp-playground/cli@latest to fetch and execute the CLI tool from the npm registry. While a standard developer workflow, the source organization is not on the explicitly trusted whitelist.
  • REMOTE_CODE_EXECUTION (LOW): The run-blueprint functionality allows the execution of site configuration logic from remote URLs. A malicious blueprint could perform unauthorized actions within the Playground environment.
  • COMMAND_EXECUTION (LOW): The skill interacts with the local file system via --auto-mount and --mount to map host directories into the virtualized WordPress environment.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection through untrusted blueprints or local files processed during the auto-mount procedure. Evidence Chain: 1. Ingestion points: --blueprint URLs and local directory paths. 2. Boundary markers: Absent in instructions. 3. Capability inventory: npx execution and local file system mounting. 4. Sanitization: No sanitization of blueprint contents or mounted file metadata is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 06:38 PM