Security audit
Security checks for vulnerabilities and agentic risk
This skill provides a disclosed local Markdown-and-SQLite memory index, with no evidence of hidden execution, network access, credential use, or destructive behavior.
Install only if you want a local, file-based long-term memory workflow. Use a dedicated memory directory, review notes before indexing them, and do not place credentials, private unrelated documents, or sensitive personal data in that directory unless you intend them to be searchable.
The skill describes file-based persistent memory, SQLite index building, and recall operations over a user-supplied memory directory, which clearly implies filesystem access. Omitting an explicit tool/permission scope means an agent may invoke the skill without a clear least-privilege boundary, increasing the chance of unintended file reads against broader local paths than intended.
The description uses broad trigger phrases like '给 bot 加记忆', '让 agent 记住之前的事', and '跨会话上下文持久化', which can match many ordinary user requests. In agentic environments, overly broad activation criteria can cause the skill to engage unexpectedly, leading to persistence of sensitive information or file operations when the user did not explicitly consent to enabling long-term memory.
The line explicitly states "中文友好" and describes a Chinese-oriented matching approach, which signals a language-specific behavior. The file does not indicate that the user can choose another language/locale or that the Chinese focus is a documented, justified regional constraint.
The docstring, CLI help text, and all user-facing print messages are written exclusively in Chinese, which indicates a fixed language choice for interaction. The file does not offer user opt-in, locale selection, or any documented justification that the skill is intended only for a Chinese-language environment.
The file's user-facing natural-language strings are entirely in Chinese, including the top-level description and usage guidance, with no indication that language selection is optional or that the skill is intentionally limited to a Chinese-only audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The argparse description and help strings shown to users are only in Chinese, and the script does not offer any mechanism to choose another language. This creates a fixed-language behavior that violates the language/locale policy unless the restriction is explicitly justified.
The entire file is written in Chinese, including the title and item descriptions, with no indication that another language is supported or that Chinese is a required locale. Under the policy for natural-language violations, forcing a specific language without user opt-in should be flagged unless the locale constraint is clearly documented and justified.
The description is written entirely in Chinese, which can indicate a language-specific constraint in the skill's natural-language metadata. The file does not offer a user language choice or explain that the note is intentionally region- or locale-specific, so it may violate the policy against forcing a specific language without opt-in.
The manifest description is written only in Chinese and provides no indication that language choice is optional or that the skill is region-specific. This can violate language/locale policy expectations when users are not offered a choice or informed justification.
The manifest description and body content are written in Chinese and describe the skill in a way that assumes a Chinese-reading user, while also embedding English technical terms. There is no indication that the skill is region-specific, no opt-in for language preference, and no alternative locale offered, which can violate a language/locale policy requiring user choice or justification.
No suspicious patterns detected.
