Security audit
Security checks for vulnerabilities and agentic risk
This skill is a brand visual identity workflow with no executable code, network behavior, credential use, or persistence.
Install this as a structured brand identity design assistant. Be aware that it may steer work through a rigid six-stage process and may use English section headings even for non-English prompts, but it does not request sensitive access or install executable behavior.
L176 states the skill 'MUST NOT generate or propose brand names, taglines, or copy' because verbal identity is outside scope. However, the required output template at L185 uses '# Brand Strategy: [Project Name]', which directs generation of a project/brand naming label in deliverables, creating a direct documentation-level contradiction about whether naming/verbal content is permitted.
This JSON eval file contains a natural-language prompt written entirely in Chinese, which implies the skill is expected to operate in a specific language context. Under the policy, forcing a specific language without user opt-in or clear justification is a locale-policy concern, and the file does not document any opt-in or region-specific limitation.
The file includes Chinese keywords in the description, suggesting multilingual use, but the mandatory output format is fixed to English labels such as 'Brand Strategy', 'Stage Progress', and 'Quality Gate Status'. This creates a locale-policy concern because the skill imposes a specific language format without offering user opt-in or documenting a justified language constraint.
This JSON file contains one English prompt and one Chinese prompt, but provides no natural-language indication that the skill supports multiple languages by user choice or that locale selection is intentional. Under the policy rule, forcing or assuming a language/locale without explicit opt-in can be a documentation-level policy concern.
