init

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests metadata from local project files to determine which framework templates to use during setup.
    • Ingestion points: The skill reads package.json and tsconfig.json files in Step 1 (SKILL.md).
    • Boundary markers: None; file contents are used for structural framework detection.
    • Capability inventory: The skill executes shell commands (npm, npx) and writes files (playwright.config.ts, playwright.yml) across various steps.
    • Sanitization: Standard detection of framework-specific strings for configuration selection.
  • [COMMAND_EXECUTION]: The skill uses documented and standard commands (npm init, npm install, npx playwright) to perform its intended installation and verification tasks. These are common operations for project setup tools.
  • [EXTERNAL_DOWNLOADS]: The skill fetches the Playwright framework and browser binaries from well-known, official repositories. These downloads are expected for the primary purpose of adding testing infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 03:48 AM
Security Audit — agent-trust-hub — init