Security audit
Security checks for vulnerabilities and agentic risk
This is a simple recall skill that clearly describes searching past conversations, with no bundled code or hidden install behavior.
Install this only if you are comfortable with the agent searching prior conversation memory when you ask recall-style questions. Review the Chinese documentation first and disable or avoid the skill if automatic memory lookup would be unwelcome.
The manifest description and all user-facing instructions are presented only in Chinese, with no indication that language is configurable or limited to a Chinese-speaking context. This can violate a language/locale policy when the skill implicitly assumes a single language without user opt-in.
The listed trigger phrases are common conversational expressions that users may naturally say outside an intent to invoke the skill. This can cause unintended automatic activation, leading to unnecessary access to historical conversation data and surprising retrieval of prior context the user did not explicitly request through a clear command boundary.
No suspicious patterns detected.
