Security audit

Cn Short Video Script

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it claims, but its helper script can automatically send user topics to OpenAI whenever an API key is present, without a clear opt-in at run time.

Install only if you are comfortable with a Chinese-language short-video scripting tool. Review or modify scripts/video_script.py before running it in an environment that contains OPENAI_API_KEY, because it may send your topic and script parameters to OpenAI automatically and use your API key unless you remove that behavior or run without the key.

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

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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

Findings (4)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill name, usage instructions, parameters, and examples are all presented only in Chinese, which effectively forces a specific language for users. The file does not mention that the skill is China-specific or provide any opt-in or alternative language option, so this appears to violate the language/locale policy criterion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: Natural-language content throughout the file, including the module description, platform names, templates, and output strings, is fixed in Chinese. There is no user opt-in, language selection, or documented justification that this is intentionally limited to a Chinese-speaking or region-specific context.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: When AI mode is enabled, the script sends the user-supplied topic directly to the OpenAI API, and the tool also auto-attempts AI generation whenever OPENAI_API_KEY is present in the environment. This can cause unintended disclosure of sensitive or proprietary topic content to a third-party service without an explicit in-context warning or affirmative consent at the moment of transmission.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.