frontend-a11y
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill's description and metadata contain instructions that attempt to override the agent's operational logic and task prioritization. The use of phrases such as "non-negotiable" and the instruction that it "applies regardless of project type, stack, or deadline" are patterns intended to force the AI to prioritize these specific instructions over other system or user-provided constraints.
Audit Metadata