Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent short-drama review helper with disclosed local review guidance and offline validators; I found no hidden network, credential, persistence, or destructive behavior.
Install this only for Chinese-language short-drama review workflows where you are comfortable letting the agent read the named project files and, when needed, write concise review Markdown. Treat the bundled Python scripts as optional offline validation/maintenance tools, not as part of normal creative review.
This duplicate mismatch finding similarly indicates the skill may actually run offline self-tests and validate JSON/JSONL review records instead of performing the advertised short-drama review task. In a review workflow, such mismatch can conceal operational behavior, confuse audit trails, and result in incomplete or incorrect security/content review outcomes.
This duplicate mismatch finding similarly indicates the skill may actually run offline self-tests and validate JSON/JSONL review records instead of performing the advertised short-drama review task. In a review workflow, such mismatch can conceal operational behavior, confuse audit trails, and result in incomplete or incorrect security/content review outcomes.
Without declared permissions the skill's intent is opaque and cannot be validated.
The description says to use the skill when the user提出“审稿/检查剧本”“检查资产或连续性”“检查图片/视频提示词”等，这些短语较宽泛，可能与普通协作对话重叠。The manifest does not provide exclusion conditions or a tighter invocation context, increasing the risk of unintended activation.
This markdown file presents all operational guidance in Chinese, and it does not indicate that the user may choose another language or that the skill is intentionally limited to a Chinese-speaking context. That creates a natural-language policy concern because it effectively forces a specific language without user opt-in.
The entire skill guidance is written only in Chinese and does not indicate that language selection is optional or configurable. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale policy violation unless the constraint is documented and justified.
The instruction requires deleted content to be listed under the Chinese heading ## 被删的强钩子, which imposes a specific language choice in the review artifact. The file does not offer a language option or explain a region-specific need, so this is a natural-language locale policy violation under the stated rule.
Line L029 states that voice direction is reviewed only when 视觉设定.md records it, and the document repeatedly relies on Chinese-language filenames and terms throughout the rubric. This natural-language framing imposes a specific language/locale convention without offering an alternative or documenting that the skill is intentionally region-specific.
The entire skill rubric is written in Chinese and provides no indication that language selection is optional or limited to a documented Chinese-only context. Under the policy rule, a skill that implicitly requires a specific language without user opt-in can be a natural-language locale violation.
This markdown file includes a Chinese heading (目录) and later substantial Chinese-only operational guidance, which imposes a specific language context on users without any opt-in or explanation. Under the policy rule, forcing a language or locale without user choice is a natural-language policy violation.
Lines 176-199 switch into Chinese for substantive review instructions and checklist content, but the document does not explain that it is region-specific or offer an alternate language. This creates an undocumented language constraint for users of the skill reference.
This JSON example contains Chinese-language path/content strings, which may impose a specific language context without any documented user opt-in or locale justification. Under the policy rule, forcing a specific language in natural-language content can be a locale-policy issue when no choice is offered.
The placeholder strings for evidence and rationale are written only in Chinese, and the file does not indicate that the skill is region-specific or that users can choose a language. This can violate the language/locale policy for natural-language content across file types.
The JSON template includes artifact path values using Chinese-language directory names in string literals, but the file provides no indication that this locale choice is optional, user-selected, or tied to a documented region-specific requirement. Because SQP-3 applies to all file types and covers forced language or locale behavior in config values, this is a mild natural-language policy concern.
Line L003 uses a Chinese heading ("目录") in an otherwise predominantly English document, and later lines also include Chinese text such as at L283 and L291. This creates a language/locale inconsistency without any stated user opt-in or justification for a bilingual or Chinese-specific audience.
No suspicious patterns detected.
