wp-playground

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the official @wp-playground/cli tool to manage WordPress instances. This tool is developed and maintained by the WordPress organization.- [INDIRECT_PROMPT_INJECTION]: The skill implements the --blueprint flag, which enables the tool to load configuration data from external URLs or local files.
  • Ingestion points: External blueprint URLs and local files are ingested via the run-blueprint command in SKILL.md.
  • Boundary markers: The skill does not provide specific instructions to the agent to treat blueprint content as untrusted data or use delimiters.
  • Capability inventory: The CLI tool can mount local directories, write snapshot files to the disk, and execute WordPress/PHP operations as defined within the blueprint.
  • Sanitization: The instructions do not specify any validation or sanitization steps for the content of external blueprints before they are executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 02:58 PM
Security Audit — agent-trust-hub — wp-playground