Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only self-review checklist skill with no code execution, credential access, network behavior, or persistence.
Install this if you want a Chinese-language, Mao-influenced structured self-review workflow. Be aware that its trigger language is broad, so agents may apply it during ordinary reviews unless you give narrower instructions.
The trigger description is broad enough to activate in many routine review, audit, or feedback situations without clear boundaries. That can cause unintended invocation of an ideologically framed critique workflow, which may steer agent behavior away from the user's immediate task or apply an inappropriate review mode in ordinary contexts.
Most of the skill content is presented in Chinese, with only a brief English trigger summary, and there is no statement that the user can choose their preferred language. This can amount to a language-policy issue because the skill effectively defaults to a specific language without opt-in or a documented region-specific justification.
The usage section lists many common situations such as finishing work, receiving feedback, or feeling uncertain, but does not define constraints, exclusions, or approval conditions. In an agent system, such broad guidance increases the chance the skill is applied by default, potentially overriding more suitable skills or introducing unnecessary self-criticism behavior into normal workflows.
The manifest description is written entirely in Chinese and presents the skill as Chinese-language content without indicating any user language choice or opt-in. Under the policy rule for language/locale constraints, this can be a natural-language policy concern when a skill appears to assume a specific language by default.
No suspicious patterns detected.
