Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Chinese content-marketing assistant with no code execution, persistence, credential access, or hidden data movement.
Install this if you want Chinese-language content marketing and social media drafting help. Be aware it may activate for broad writing or content-strategy prompts, so users who only want narrow opt-in behavior may prefer clearer trigger wording, but there is no artifact evidence of hidden execution, data access, or persistence.
The trigger phrases are very broad and map to common user intents like writing copy, content strategy, and social media help. This can cause the skill to activate in situations where the user did not explicitly request this specialized behavior, increasing the chance of unintended instruction injection, role hijacking, or output shaping by the skill over normal assistant behavior.
The rule 'when the user issues a content creation request' is underspecified and effectively authorizes automatic activation for a very large class of normal requests. In practice, this broad condition can make the skill overtake standard handling for many unrelated or mixed-context prompts, which expands attack surface and makes prompt-routing behavior less predictable.
The natural-language instructions, trigger phrases, and examples are all presented in Chinese, and the file does not state that users may choose another language. This can be a locale/language policy issue when a skill implicitly forces one language without explicit opt-in or justification.
No suspicious patterns detected.
