Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only memory organization skill with disclosed storage concepts and no executable code, though users should avoid storing sensitive material unintentionally.
Install only if you want an agent memory-formatting guide. Review what the agent stores, avoid placing secrets or highly sensitive personal data into memory, and prefer explicit /mempalace invocation because keyword triggering is not tightly specified.
The phrase "trigger keywords" is underspecified and can cause the skill to activate in unintended contexts. In an agent environment, vague activation conditions increase the chance of accidental invocation, prompt-routing mistakes, or abuse via crafted inputs that match undocumented triggers.
This markdown/manifest file describes the skill's capabilities but does not define explicit trigger phrases, scope boundaries, or exclusion conditions. Without clear activation criteria, the skill could be invoked in overly broad contexts whenever memory, compression, or integration is mentioned.
The skill explicitly states that original content is retained and summaries are stored, but it provides no consent, retention, minimization, or sensitive-data handling guidance. In a memory/persistence skill, this can lead to inadvertent long-term storage of private user data, secrets, or regulated information, increasing privacy and data-exposure risk.
This markdown file is primarily written in Chinese, which can violate a language/locale policy when a skill forces a specific language without user opt-in. Although there is a link to an English file at L05, this file itself does not present the content bilingually or state that the language is optional.
The visible natural-language description and instructions are entirely in Chinese, with no indication that other languages are supported or that the user can opt into this locale. That can violate language/locale policy when a skill implicitly constrains interaction language without user choice.
No suspicious patterns detected.
