keyboard-navigation

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a reference guide for accessibility best practices, specifically focus management and keyboard interactions. No unauthorized command execution, credential access, or malicious persistence mechanisms were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to analyze externally provided HTML and rendered markup. This creates a surface for indirect prompt injection if the analyzed content contains hidden instructions. However, because the skill defines no executable capabilities or tool access, the potential for exploitation is neutralized.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 01:59 PM