Use as the WordPress Playground routing wrapper for ambiguous Playground work, local CLI runs with @wp-playground/cli, playground.wordpress.net share links, browser previews, snapshots, mounts, version switching, and Xdebug. For Blueprint JSON authoring or review, use the blueprint skill directly.
80
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The `website` runtime workflow for `https://playground.wordpress.net/` ingests outsider-authored free text when an attacker supplies a `#...` inline Blueprint fragment or a `?blueprint-url=<url>` that loads public Blueprint JSON/ZIP content, which the agent then uses to drive site setup.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
The skill allows loading remote Blueprints and site setup via the Playground website (e.g., https://playground.wordpress.net/ and the example https://playground.wordpress.net/?php=8.4&wp=latest&plugin=gutenberg&networking=yes&url=/wp-admin/post-new.php), and the CLI also accepts --blueprint=<file-or-url>, so external URLs fetched at runtime can supply Blueprint JSON/ZIP that directly control environment setup and execute code or steps.
120d309
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.