wp-playground

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and fetches blueprints from public URLs (see "Run a Blueprint" in SKILL.md and references/blueprints.md and the browser query param ?blueprint-url=<public-url-or-zip>), and those blueprints can contain executable steps like runPHP, writeFile, and installPlugin that the agent will interpret and act on, so untrusted third-party content can materially influence behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 03:43 PM