Natural-Language Policy Violations
Medium
- Confidence
- 86% confidence
- Finding
- The generated prompt hard-codes a demographic attribute ('Asian female model') without user opt-in, which can embed bias, create discriminatory outputs, and produce inappropriate or policy-violating content in downstream image generation systems. While this is not a classic code-execution issue, the skill context makes it more concerning because it directly shapes generated creative assets at scale and may systematically enforce sensitive-attribute defaults.
