Security audit

AI视频分镜提示词导演

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language prompt-writing skill for AI video storyboards, with no executable code or hidden system access.

Installers should expect this skill to produce Chinese-formatted AI video prompts and may need to ask explicitly for another language if desired. Avoid providing confidential product images or unreleased creative assets as references unless you are comfortable using them with the downstream video model.

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (5)

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The README is entirely written in Chinese and specifies fixed Chinese output phrases such as the automatically appended negative prompt terms, but it does not indicate that users may choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The manifest description is written entirely in Chinese and frames the skill as producing prompts in that language, with no indication that users may choose another language or locale. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The core overview defines the skill's behavior entirely in Chinese and does not provide any option for matching the user's preferred language. Because the file contains prescriptive natural-language instructions for the skill, the absence of language choice indicates a forced locale/language policy issue.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: This markdown file presents the scoring rubric entirely in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy rule, forcing a specific language without user opt-in is a natural-language policy concern.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The entire test case file is written as Chinese-only instructions and expected inputs/outputs, with no indication that the user can choose another language or locale. Under the policy rule for language/locale constraints, this reads as a fixed-language requirement rather than an optional or justified regional setting.

Static analysis

No suspicious patterns detected.