Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple prompt and agent-design helper with no code execution, credential access, persistence, or hidden behavior.
Before installing, note that this is a lightweight prompt-design aid and may route on broad agent/prompt optimization requests; users who prefer another language may need to ask the agent to respond in that language.
The invocation examples are very broad and do not define clear boundaries for when the skill should activate. In an agent environment, this can cause over-triggering or inappropriate routing, leading the assistant to apply prompt-engineering behavior in unintended contexts and potentially interfere with safer or more specific skills.
The description is written in mixed Chinese and English, and the document consistently presents content in that mixed language style without stating that users may choose their preferred language or locale. This can be a language-policy issue if the organization expects user opt-in before imposing a specific language or dialect.
No suspicious patterns detected.
