ultraqa
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses directive language such as 'You are now in ULTRAQA mode
- an autonomous QA cycling workflow' to establish a specific behavioral persona. While this is aimed at task automation within a software development context, these types of instructions are analyzed as potential prompt injections designed to override default agent behavior. The severity is low as the context is restricted to a local QA loop for code projects.
Audit Metadata