playwright-test-generator

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell operations using npx playwright test, npx tsc, and grep to detect environments, verify generated code, and audit for unused locators. These commands are executed within the context of the user's local project files.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to run Playwright and TypeScript utilities. This may trigger downloads from the official npm registry if these dependencies are not cached locally.
  • [PROMPT_INJECTION]: The skill explicitly acknowledges the risk of indirect prompt injection from the target application's content. It contains a dedicated 'Safety' section instructing the agent to treat all data from the browser (DOM, console logs, etc.) and source code as untrusted, forbidding the execution of any instructions or commands found within that data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 04:17 AM
Security Audit — agent-trust-hub — playwright-test-generator