Security audit

ai视频人物真实性方法论

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only AI video prompt and cinematography guide with no code execution, credential access, persistence, or destructive behavior.

Install this if you want a Chinese-language AI video cinematography and prompt-writing reference. Be aware that it may be invoked for broad AI video or image prompt requests, and users who prefer another language may need to ask explicitly for translation or adaptation.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (5)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The manifest description says 'Use when' followed by very broad situations such as 'Generating AI videos' and 'Writing video/image prompts,' which overlap with many ordinary creative requests. It does not provide narrower trigger phrases, exclusions, or negative examples to distinguish when this skill should be invoked versus other general writing or media-generation skills.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The manifest description is written to specify an "AI视频创作" guide, which indicates a Chinese-language requirement or default without offering any user language choice. The policy requires avoiding forced language or locale constraints unless they are explicitly justified or opt-in.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: The title and description are written primarily in Chinese with embedded English terminology, but there is no statement that the skill can adapt to the user's preferred language. Under the policy, forcing a specific language or locale without opt-in can be a natural-language policy issue.

Natural-Language Policy Violations

Low

Confidence: 92% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This reference document presents all instructional content in Chinese only and does not indicate that users may choose another language or that the locale restriction is intentional or region-specific.

Natural-Language Policy Violations

Low

Confidence: 86% confidence
Finding: This markdown file contains natural-language instruction that steers users toward a specific language: '组合英文提示词'. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation unless the constraint is clearly justified or alternatives are offered.

Static analysis

No suspicious patterns detected.