security-hygiene

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed for passive observation of security hygiene and explicitly prohibits intrusive actions such as injection payloads, authentication bypass, or reconnaissance.
  • [PROMPT_INJECTION]: The skill ingests untrusted external data during its analysis, presenting a surface for indirect prompt injection.
  • Ingestion points: Browser-rendered HTML content, HTTP response headers, cookie attributes, and JavaScript source files discovered while crawling.
  • Boundary markers: There are no explicit delimiters or instructions to treat external data as untrusted text rather than instructions.
  • Capability inventory: The skill uses Playwright for browser automation, makes network requests, and generates CSV reports.
  • Sanitization: The instructions do not define any sanitization or validation for data retrieved from external websites.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 03:54 AM
Security Audit — agent-trust-hub — security-hygiene