Security audit
Security checks for vulnerabilities and agentic risk
This skill is a Chinese-language helper for generating cinematic action-scene video prompts and does not request code execution, file access, credentials, persistence, or external network behavior.
Install this if you want Chinese-language cinematic action video prompt generation. Expect it to steer responses into a structured action-shot format when invoked by broad action or fight-related terms.
The trigger phrases are broad action-related terms with no scope limits, so the skill may activate in contexts where the user did not intend to invoke this specialized behavior. That can cause prompt hijacking of unrelated conversations and steer outputs toward violent action-scene generation, which is more concerning because the skill is explicitly centered on combat and fighting content.
The skill enforces a fixed output style and formatting regime without checking the user's preferred language or presentation format. While not directly a code-execution or data-exfiltration issue, it can override user intent, reduce usability, and make the agent less reliable by forcing a preset response structure even when the user asks for something else.
The display name, short description, and default prompt are all written only in Chinese, which imposes a language choice on users without any opt-in or alternative locale support. This matches the policy category for language or locale constraints that are not user-selectable or explicitly justified.
No suspicious patterns detected.
