qa-ui

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed entirely of markdown instructions and does not include any scripts, binaries, or automated code execution.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its requirement to interact with external content.\n
  • Ingestion points: File SKILL.md (Step 1 and Step 2) instructs the agent to navigate to user-provided URLs or local ports and walk through the product's screens.\n
  • Boundary markers: The instructions do not provide delimiters or specific guidelines for the agent to ignore instructions that might be embedded in the text or HTML of the target website.\n
  • Capability inventory: The agent is granted browser navigation and screenshotting capabilities to document the UI.\n
  • Sanitization: There is no mechanism for sanitizing or filtering the content found on external pages before the agent processes and screenshots it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 08:59 PM