test-red-team

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the Playwright CLI from the official package registry using npx to facilitate browser-based testing. This is an expected dependency from a trusted vendor.- [COMMAND_EXECUTION]: Utilizes shell commands through Playwright and the Android Debug Bridge (ADB) for UI automation and network emulation, which is consistent with the skill's purpose of application testing.- [DATA_EXFILTRATION]: Accesses project configuration files and database content to assess application security. The skill includes explicit instructions to handle secrets by name only and to use benign data for confirming findings.- [PROMPT_INJECTION]: The skill processes external source code and database data, which presents an attack surface for indirect prompt injection. This is addressed through safety guidelines that require manual browser sessions and the use of explicit test data markers.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 05:56 AM
Security Audit — agent-trust-hub — test-red-team