qa-systematic

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill dynamically identifies and runs test commands such as 'make test', 'npm test', or 'pytest' by inspecting project files like 'package.json' and 'Makefile' via project detection logic.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it systematically explores and processes content from target web applications during testing.
  • Ingestion points: Web page HTML, navigation structures, and form elements collected in Phase 3 and Phase 4.
  • Boundary markers: Not specified; the agent lacks explicit delimiters to distinguish between target application data and internal QA instructions.
  • Capability inventory: Browser automation (Playwright/Puppeteer) and shell command execution (test runners).
  • Sanitization: No methods for sanitizing or validating external web content are mentioned in the skill instructions.
  • [EXTERNAL_DOWNLOADS]: The skill depends on external browser automation frameworks such as Playwright, Puppeteer, or Cypress, and attempts to utilize them if found on the system PATH.
  • [CREDENTIALS_UNSAFE]: The authentication workflow involves requesting or utilizing user-provided credentials to test password-protected features of the target application.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 11:21 AM
Security Audit — agent-trust-hub — qa-systematic