Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent automation-planning skill, but it needs review because it encourages persistent scheduled execution without clear user-control and containment guidance.
Review this skill before installing if you do not want agents to structure work as scheduled or recurring automation. For any use, require explicit approval before registering jobs, define where logs go, avoid logging secrets, set retention limits, and make every scheduled task easy to pause or delete.
The trigger phrases are broad and include common terms like '自动化', '定时任务', '调度', and especially 'meta-skill-system', which can match many ordinary user requests outside the intended scope. This can cause the skill to activate unintentionally, injecting its workflow and execution framing into unrelated conversations and increasing the chance of overreach or unsafe autonomous behavior.
The document is written entirely in Chinese and line L003 instructs outputs to be produced according to the checklist without offering any language choice. This creates a natural-language policy concern because the skill content appears to require a specific language/locale by default rather than letting the user opt in or choose their preferred language.
The entire skill reference and template are written as Chinese-only instructions and labels, with no indication that users may choose another language or that the locale restriction is required for a region-specific purpose. This can violate language/locale policy because it implicitly forces a specific language without user opt-in.
This markdown file presents all task instructions, examples, and notes exclusively in Chinese. Under the policy rules, forcing a specific language without user opt-in or a documented justification can be a natural-language policy violation.
This markdown file presents all instructions, examples, and labels only in Chinese, which can amount to a language/locale policy violation when no user opt-in or documented regional justification is provided. The stated policy requires flagging skills that force a specific language without offering choice.
This markdown file uses a single fixed language throughout, and there is no natural-language indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without opt-in can be a locale-policy violation.
The template recommends storing execution logs on the local filesystem and emphasizes completeness, but it does not mention access controls, retention limits, or the possibility that logs may contain sensitive operational details and error data. In an automation framework, such logs can expose task behavior, resource usage, timings, and failure information that could aid reconnaissance or leak sensitive runtime context if improperly accessible.
No suspicious patterns detected.
