compatibility-testing

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows security best practices for credential management by utilizing environment variables for BrowserStack authentication in its configuration examples.
  • [SAFE]: No obfuscation, unauthorized network operations, or malicious persistence mechanisms were found across the skill files.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill processes external URLs and code snippets (CSS/JS) for compatibility analysis as part of its testing workflow (SKILL.md, evals/compatibility-testing.yaml).
  • Boundary markers: No explicit boundary markers are defined to isolate untrusted code from instructions.
  • Capability inventory: The skill executes testing tasks through Playwright and coordinates agent fleets for parallel testing.
  • Sanitization: Relies on the security boundaries of the underlying automation tools (Playwright) during execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 12:39 PM