Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a brand-design guide, but it asks for broad read, write, and command-execution capability without enough scoping and includes unrelated network troubleshooting instructions.
Review this skill before installing. It appears to be a Markdown-only brand identity helper, not malware, but its declared command execution and broad file access are not tightly scoped. Use it only in a workspace where generated brand assets can safely be written, and avoid following its network/firewall troubleshooting guidance unless you intentionally want system diagnostics.
The skill declares read, exec, and write capabilities but does not clearly warn users that it may execute commands or modify files. In an agent environment, undisclosed execution and file-write permissions materially raise risk because users may invoke what appears to be a harmless design skill without understanding its ability to affect the local system or workspace.
The capability coverage text is extremely broad and keyword-driven, making the trigger conditions ambiguous and easier to match in unrelated contexts. Overly broad activation increases the chance that the skill is invoked when the user did not intend a brand-design workflow, which is more concerning because the skill also advertises exec and write tools.
The skill is for brand identity design, but its error-handling guidance instructs the agent to run network diagnostics such as ping and adjust firewall/proxy settings. That expands behavior into system and network operations unrelated to the stated purpose, creating an unnecessary path for command execution and environmental probing if a user or downstream workflow follows the guidance.
The display name, summary, and description are presented entirely in Chinese, and the document does not mention any user-selectable language or locale option. Under SQP-3, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.
The documentation says this capability supports create/query/export operations via input_params without explaining what resources are affected or constraining those operations to brand-design artifacts. In an agent setting, vague operational verbs can cause over-broad invocation and unintended data handling or file generation beyond the skill's legitimate scope.
