Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only Chinese short-drama writing skill with broad creative-writing routing, but no code, credential access, persistence, or hidden system behavior.
Install this if you want a Chinese short-drama or AI manga writing workflow. Be aware it may strongly steer broad script, outline, and plot requests into this format and may add ViFlow JSON exports by default; review generated violence, platform-policy claims, and market statistics before using the output commercially.
The skill advertises automatic triggering for broad user intents such as writing scripts, outlines, plot design, and mentioning ViFlow import. Overly broad activation can cause the wrong skill to engage unexpectedly, steering user interactions and outputs without clear user intent, which is a prompt-scope and reliability issue rather than a code-execution flaw.
The phrase indicating the skill should 'automatically trigger' when users discuss certain topics is ambiguous and can be interpreted too aggressively by an agent system. In practice this can lead to unintended invocation, context hijacking of adjacent requests, and outputs shaped by the skill when the user did not clearly opt in.
The schema requires 'imagePrompt' to be in English, which is a language constraint stated as mandatory and not presented as a user choice. This is a natural-language policy concern because it forces a specific language without opt-in or justification.
The schema specifies 'videoPrompt' as an English prompt, again enforcing a fixed language requirement. The file does not offer an alternative language choice or explain why English is mandatory for all users.
This JSON manifest/schema uses Chinese natural-language field examples and values throughout, and does not indicate that the skill is intentionally region-specific or that users may choose another language. That creates a natural-language locale constraint without opt-in, which falls under the policy-violation category.
This JSON template hard-codes the title, metadata, dialogue, prompts, and branding text in Chinese throughout the file. Under the policy, forcing a specific language without user opt-in or a clearly documented region-specific justification is a natural-language policy violation.
The entire skill file is written in Chinese and provides no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without opt-in is a natural-language policy violation.
The natural-language content contains a direct threat of serious physical harm: '打断你双腿' ('break your legs'), followed by an instruction to attack. While this is presented as fiction, it is still a natural-language pattern encouraging violence and lacks any contextual note that it is purely dramatic content.
This markdown file is entirely written as a Chinese script example and provides no indication that language selection is optional or that the skill is intended only for a Chinese-language context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
This file presents all instructions and templates exclusively in Chinese, with no indication that the user can choose another language or that the locale restriction is intentional. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
This markdown file is entirely framed as a Chinese-language script template and includes instructions such as Chinese dialogue, narration, and audio/style guidance without indicating that language selection is optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless clearly justified as region-specific, which is not stated here.
Natural-language policy violations apply to all file types, including markdown. This skill content forces a specific language/locale for all users and does not provide opt-in, alternatives, or a stated region-specific purpose that would justify the constraint.
The title and all narrative content are written in Chinese, and the file provides no indication that language choice is optional or user-selectable. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is documented and justified.
The entire skill guidance is written as a prescriptive Chinese-only content framework, including required output structures and declarations, but it does not offer any language or locale choice. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless clearly justified as region-specific.
The entire skill file is written exclusively in Chinese and does not indicate any option for the user to choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This markdown template presents all instructions and examples only in Chinese, with no indication that the skill is region-specific or that users may choose another language.
This markdown file is entirely presented in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The skill hard-codes a specific nationality/locale ('Chinese', 'ancient Chinese fantasy style') into reusable generation prompts without any indication that the user explicitly requested that constraint. This can override user intent, reduce cultural flexibility, and create biased or exclusionary outputs when the same template is reused broadly.
No suspicious patterns detected.
