e2e-testing
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a standard high-level workflow for browser automation and testing without any executable code or suspicious instructions.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill proactively warns users that test artifacts (traces, screenshots, videos, storage-state) may contain credentials or private data and instructs users to redact them before sharing.
- [INDIRECT_PROMPT_INJECTION]: The skill outlines a workflow for browser automation which involves processing external web content.
- Ingestion points: Web applications and pages processed during Phase 3 (Implementation) and Phase 4 (Automation).
- Boundary markers: The 'Scope and proof' section provides explicit warnings to isolate fixtures and use approved sandbox endpoints.
- Capability inventory: Invokes external skills for Playwright automation, browser interaction, and CI/CD integration.
- Sanitization: Instructions explicitly recommend redacting artifacts before sharing to prevent data leakage.
Audit Metadata