webapp-testing

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected in this skill. The skill follows standard browser automation patterns using the well-known Playwright library. While it mentions the automatic installation of Playwright, this is consistent with its primary purpose as a testing utility. The skill exhibits an indirect prompt injection surface common to web scrapers and browsers, as it ingests content from external web pages.
  • Ingestion points: Web page content, browser titles, and console logs are read into the agent's context (SKILL.md, test-helper.js).
  • Boundary markers: None identified.
  • Capability inventory: Browser navigation, element interaction, and screenshot capture (SKILL.md).
  • Sanitization: No explicit sanitization of external web content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 12:20 AM
Security Audit — agent-trust-hub — webapp-testing