Security audit
Security checks for vulnerabilities and agentic risk
The skill is a logo-design guide with no malicious code, but it asks for command execution and file-writing authority that is not clearly needed or scoped.
Review this skill before installing if your agent grants declared tools automatically. It appears to be design guidance, not malware, but its command execution and file-writing permissions should be removed or tightly limited unless you specifically need the agent to create or modify local logo-related files.
The description is broad enough to match many generic design or development requests without clear trigger constraints. Over-broad activation increases the chance the skill is selected in irrelevant contexts, where its unnecessary tools or permissive instructions could be exposed.
The skill requests read/exec/write capabilities even though its stated purpose is a logo design guide and instructional workflow. This creates unnecessary authority and expands the attack surface: if the skill is auto-invoked or its instructions are later extended, it could modify files or execute commands unrelated to the user’s design task.
The skill advertises exec/write-capable behavior without any warning, permission model, or discussion of filesystem/system side effects. When a skill can execute commands or write files, omitting guardrails makes accidental or unsafe actions more likely, especially if the skill is invoked automatically for routine design requests.
The document presents the free version as guidance-only, but later describes create/query/export operations and structured execution outputs as though the skill performs active actions. This mismatch can mislead the agent runtime or users into granting operational trust and tool usage that exceeds the intended safe scope.
The capability coverage section lists fragmented, vague, and highly generic keywords that could match a wide range of unrelated requests. In an agent routing system, this can cause over-selection of the skill and increase exposure of its exec/write permissions beyond the intended logo-guidance context.
The display name, summary, and nearly all instructional content are presented in Chinese, with no indication that users may choose another language or locale. This can be a language/locale policy issue when a skill implicitly fixes the interaction language without opt-in or justification.
No suspicious patterns detected.
