Security audit
Security checks for vulnerabilities and agentic risk
This is a small local memo skill whose behavior matches its purpose, with minor documentation and deletion-confirmation caveats.
Install only if you are comfortable with a local memo tool that stores notes in a JSON file under your home directory and permanently deletes memo entries when delete_memo is invoked. Be careful with completion-style requests, since the skill treats at least one such phrase as deletion rather than marking a note complete.
The declared description says this skill provides note-taking features including recording, querying, and deleting notes. However, the supplied code chunk contains only an empty TypeScript declaration file (export {};) and shows no implemented logic, storage, triggers, or permissions. This is a material mismatch because the actual code does not demonstrate the claimed primary purpose or capabilities at all.
Referenced artifact was not completely inspected
node dist/index.js <action> <content>
Referenced artifact was not completely inspected
node dist/index.js <action> <content>
Referenced artifact was not completely inspected
node dist/index.js <action> <content>
Referenced artifact was not completely inspected
node dist/index.js <action> <content>
Referenced artifact was not completely inspected
node dist/index.js <action> <content>
Referenced artifact was not completely inspected
node dist/index.js <action> <content>
Referenced artifact was not completely inspected
node dist/index.js <action> <content>
The README content is presented in Chinese and does not indicate that other language options are available or that the skill is intentionally restricted to a Chinese-speaking context. The policy requires avoiding forced language or locale constraints unless the user can opt in or the restriction is clearly justified.
Without declared permissions the skill's intent is opaque and cannot be validated.
The documentation presents delete_memo as a normal action without warning that it permanently removes data. In an agent setting, lack of disclosure around destructive behavior increases the chance of accidental invocation and irreversible loss of user notes.
The delete rule maps a natural-language phrase like '第3条备忘完成了' directly to a destructive deletion command without confirmation. This can cause unintended data loss when a user is merely marking an item as completed rather than explicitly asking to erase it, especially in conversational contexts where intent can be ambiguous.
The delete_memo branch removes data from the in-memory memo list and immediately persists the change to disk, making the deletion effectively destructive. While there is a post-action log message, there is no pre-action warning, confirmation prompt, or explanatory comment/docstring disclosing that the operation permanently modifies the stored memo database.
The markdown usage section includes a delete operation for memo entries, which affects user data, but the description provides no caution or warning about data removal. Under the markdown-file criteria, behaviors that can affect user data should be disclosed clearly.
The operational instructions and trigger phrases are presented only in Chinese, implying a fixed language for invocation and use. The file does not offer a language choice or document that the locale restriction is intentional and justified.
The file contains multiple user-facing comments and console messages in Chinese, and the skill provides no indication that language is configurable or intentionally limited to a Chinese-speaking audience. This can violate a language/locale policy when users are not given an explicit opt-in or documented locale scope.
No suspicious patterns detected.