qa-analyzing-ux-flows

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The script scripts/accessibility_check.py fetches the axe-core library from cdnjs.cloudflare.com. This is a well-known and reputable service for hosting web assets.
  • [COMMAND_EXECUTION]: The skill uses local Python scripts to audit websites and analyze user flows. These scripts are run via the command line and generate reports in the local filesystem.
  • [PROMPT_INJECTION]: The skill audits external websites and extracts content such as HTML attributes and labels, creating a surface for indirect prompt injection.
  • Ingestion points: The scripts/accessibility_check.py script extracts metadata and text from target URLs.
  • Boundary markers: Extracted content is included in reports without specific delimiters or instructions to ignore embedded commands.
  • Capability inventory: The skill can write files to the local directory and access network resources to perform audits.
  • Sanitization: The script truncates HTML snippets for brevity but does not sanitize extracted text against potential injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 03:29 AM