qa-element-extraction
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and code snippets for UI testing. No executable scripts, malicious patterns, or obfuscation techniques were detected in the provided file.
- [PROMPT_INJECTION]: The skill defines a process for parsing external test documents (
QA-*.md) and web pages. This constitutes an indirect prompt injection surface where malicious instructions could be embedded in test steps or web elements. - Ingestion points: External test procedures in markdown files and live web page content via Playwright.
- Boundary markers: Absent; the skill does not define delimiters to separate test data from agent instructions.
- Capability inventory: Screenshot capture, page navigation, and element interaction via Playwright MCP.
- Sanitization: Not specified; the skill assumes test documents are trusted sources.
- [DATA_EXFILTRATION]: Automated screenshot capture of UI elements inherently carries a risk of exposing sensitive data (e.g., PII, session tokens, or internal configurations) if the test environment is not properly sanitized. However, no evidence of exfiltration to unauthorized domains was found.
Audit Metadata