Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese content strategy and editing review skill with no executable code, network access, credential handling, persistence, or hidden high-impact behavior.
Install this if you want a Chinese-first editorial review assistant for self-media strategy. Users needing multilingual or general-purpose writing help may need to explicitly ask for another language or adapt the prompts, but no security-sensitive behavior was found.
The markdown explicitly states the assistant is a Chinese self-media content director and frames the role around producing Chinese-language content for a specific persona. This is a natural-language locale constraint, but the file does not offer opt-in or an alternative language choice, which can violate language-choice policy.
The title and checklist are entirely in Chinese, which indicates the skill is constrained to a specific language without any visible note that users may choose another language. Under the policy, language-specific behavior should either be optional or explicitly justified as region-specific.
The entire instruction set is written as a mandatory Chinese execution prompt for the subagent, with no indication that the user may choose another language or locale. This can violate language/locale policy when a skill implicitly forces a specific language without explicit user opt-in.
