Security audit
Security checks for vulnerabilities and agentic risk
This is a static Chinese-language advice skill for self-media content strategy, with no code execution, data access, persistence, or privileged behavior.
Install this only if you want Chinese-language self-media trend and platform advice. Treat the recommendations as static guidance, not verified live market research or platform policy updates.
The skill description uses broad trigger phrases like “做什么内容” and “自媒体趋势,” which can overlap with ordinary user queries and cause the skill to activate outside narrowly intended contexts. Over-broad activation can lead to unintended routing, prompt hijacking surface expansion, and lower-confidence advice being injected into unrelated conversations.
The skill is entirely hard-coded in Chinese without declaring a locale restriction or offering language selection, which can cause misrouting or unsafe misunderstandings for users operating in other languages. In a skill-selection pipeline, this increases the chance of the wrong skill being invoked and reduces transparency about capability boundaries.
No suspicious patterns detected.
