Security audit
Security checks for vulnerabilities and agentic risk
This skill is mostly a disclosed chat-productivity note, but it has broad trigger phrases and describes chat history/cache behavior users should understand before using.
Before installing, be aware that the skill is documented mainly in Chinese, uses broad activation phrases, and describes storing conversation history and cached responses. Use it only if you are comfortable with chat content being retained by the intended implementation, and prefer narrower trigger wording if your agent supports it.
The trigger phrase "Chat" is extremely broad and is likely to match many ordinary user requests unrelated to this specific skill. In an agent environment, this can cause unintended skill activation, prompt/context hijacking, or inappropriate routing of sensitive conversations into this skill's logic and history/cache features.
Most user-facing instructions and descriptions in the skill are presented only in Chinese, which effectively forces a language choice on users without opt-in. The file does not state that the skill is intentionally region-specific or provide an alternative language path.
The trigger phrase "marginnote" is ambiguous and may activate on general discussion of the MarginNote product rather than an intentional request for this skill. This increases the chance of accidental invocation and unintended access to the skill's conversation-management behaviors.
No suspicious patterns detected.
