Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward Chinese weekly-report writing skill with no hidden code execution, credential access, or destructive behavior.
Install only if you are comfortable giving the assistant your work-project context and, if using the copy-paste prompt with an external AI service, make sure that service is acceptable for your workplace information.
The trigger phrases "帮我写周报" and "把这段流水账升级成周报" are broad natural-language requests that a user could say in many ordinary contexts, increasing the chance this skill activates unintentionally. Over-broad activation can cause prompt/skill routing collisions, unexpected access to user-provided work content, and execution of this skill when the user intended a different assistant behavior.
The description and core instructions are entirely in Chinese and frame the skill around producing a Chinese-format leadership report, with no indication that the user may choose another language. This creates a natural-language locale constraint without documented opt-in or justification, which matches the language/locale policy violation criteria.
This markdown example presents all instructions, labels, and outputs exclusively in Chinese, which can amount to a language/locale constraint in the skill's natural-language interface. The file does not indicate that Chinese is optional, user-selected, or required for a specific regional purpose.
The entire prompt template is written as a prescriptive Chinese-only interaction flow and does not mention any option to use another language. This is a natural-language locale policy concern because it imposes a specific language without documenting user choice or a justified regional constraint.
No suspicious patterns detected.
