Security audit
Security checks for vulnerabilities and agentic risk
This skill is mostly transparent about lifecycle automation, but it asks the agent to run background/session-end automation and write memory without enough scoping or user control.
Review this before installing if you do not want an agent to create session-end cron tasks, run heartbeat-driven checks, spawn subagents, or write daily memory logs automatically. Installation should be acceptable only if you are comfortable with lifecycle automation and can clearly control when hooks are enabled or disabled.
The trigger phrases are very broad and include natural-language requests such as “检查生命周期钩子” and “记忆自动捕获怎么配置”, which can plausibly occur in ordinary conversation. This creates a prompt/skill invocation ambiguity where the skill may activate unintentionally and perform automation behavior such as cron scheduling, memory writes, or subagent orchestration without a clearly scoped user intent.
The description says the skill triggers custom actions on 'critical events' but does not define what events are in scope, who can trigger them, or what constraints apply. For a lifecycle-hook skill, ambiguous activation language increases the chance the agent will invoke automation too broadly, including on sensitive phases such as startup, message handling, or subagent execution, which can lead to unintended actions or privilege misuse.
The description contains Chinese-language text in the skill metadata, but there is no indication that the skill is intended only for Chinese-speaking users or that language choice is configurable. This may create a language/locale policy issue because the skill appears to impose a specific language without documented opt-in or justification.
No suspicious patterns detected.
