Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language knowledge-organization guide with disclosed local note-writing suggestions and no executable code, network access, credential use, or hidden behavior.
Install only if you want a Chinese-language workflow for organizing learning materials. Before allowing it to write into a wiki or AGENTS.md, review the proposed changes and keep human verification in place because AI-generated notes can contain mistakes.
The skill’s natural-language instructions and examples are entirely in Chinese, and no opt-in or language-selection mechanism is provided. Under the language/locale policy, forcing a single language without user choice can be a policy violation unless the locale restriction is explicitly documented and justified.
The skill explicitly promotes writing synthesized outputs back into a wiki/knowledge base, but it does not require an explicit warning or consent step before modifying user data. In an agent setting, this can lead to unintended persistent changes, propagation of hallucinated content, and silent corruption of notes or documentation.
The trigger phrases are broad enough to match common learning and organization requests, which can cause the skill to activate outside the user’s intended scope. That increases the chance of unsolicited steering into this workflow, including downstream actions like knowledge-base organization or suggested write-back behavior.
No suspicious patterns detected.
