Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Chinese technical-blog writing skill whose main caveat is that it tells the agent to save the generated post as a Markdown file in the current project.
Before installing, understand that this skill may cause the agent to create a Markdown blog file in the current project; review the filename and destination if preserving existing project files matters.
The natural-language instructions and output conventions are entirely Chinese, and the skill does not indicate that language selection is optional or user-controlled. This can violate language/locale policy when a skill implicitly forces a specific language without opt-in.
The skill explicitly instructs the agent to save generated content as a .md file in the current project without requiring user confirmation or constraining the path. That creates an unauthorized file-write behavior risk: an agent could modify the workspace unexpectedly, overwrite existing documentation, or persist unreviewed content into a repository.
No suspicious patterns detected.
