Security audit

china-video-gen

Security checks for vulnerabilities and agentic risk

Overview

The skill appears purpose-aligned for AI video generation, but it asks users to install mutable third-party skills and persist an API key without enough scoping or secret-handling guidance.

Review this skill before installing. It is not showing malicious behavior, but use a dedicated low-quota SiliconFlow key, avoid storing it permanently unless the file is locked down, and verify or pin the china-image-gen and china-tts dependencies before granting them access to your workspace or credentials.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: references/dependencies.md:76
Finding: Persistent Plaintext Storage of SiliconFlow API Credential
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Warning

Location: references/dependencies.md:34
Finding: Unpinned Installation of Third-Party OpenClaw Skills
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (12)

Chaining Abuse

High

Category: Tool Misuse
Confidence: 75% confidence
Finding: Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.
Content: Scanner excerpt · references/dependencies.md (reported line 15)May include surrounding context.
md
brew install ffmpeg # Ubuntu/Debian sudo apt update && sudo apt install -y ffmpeg # CentOS/RHEL sudo yum install -y ffmpeg

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description advertises video generation capabilities but does not clearly warn that user text and derived prompts will be transmitted to external services for image and speech generation. This creates a privacy and consent risk, especially if users provide sensitive marketing drafts, personal data, or proprietary material expecting only local handling.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger phrases are very broad and map to common user requests like 'make a promo video' or 'turn this text into a video', which increases the chance the skill auto-activates in situations where the user did not explicitly consent to using external generation services. In this skill’s context, that means user-provided content may be sent to third-party image/TTS APIs and local media-processing tools without a clear, narrow activation boundary.
Content: No source excerpt is available for this finding.

Sudo/Root Execution

Medium

Category: Privilege Escalation
Confidence: 70% confidence
Finding: Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
Content: Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.
text
检查 ffmpeg 是否已安装： - macOS: brew install ffmpeg - Ubuntu: sudo apt install ffmpeg - Windows: 从 https://ffmpeg.org/download.html 下载

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: Step 2 specifies that the image prompt should be in English and the narration should be in Chinese, even though Step 1 says the user language may be Chinese, English, or mixed. This creates a fixed language requirement that overrides the user's stated preference without clear justification or opt-in.
Content: No source excerpt is available for this finding.

Sudo/Root Execution

Medium

Category: Privilege Escalation
Confidence: 70% confidence
Finding: Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
Content: Scanner excerpt · references/dependencies.md (reported line 15)May include surrounding context.
md
brew install ffmpeg # Ubuntu/Debian sudo apt update && sudo apt install -y ffmpeg # CentOS/RHEL sudo yum install -y ffmpeg

Sudo/Root Execution

Medium

Category: Privilege Escalation
Confidence: 70% confidence
Finding: Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
Content: Scanner excerpt · references/dependencies.md (reported line 18)May include surrounding context.
md
brew install ffmpeg # Ubuntu/Debian sudo apt update && sudo apt install -y ffmpeg # CentOS/RHEL sudo yum install -y ffmpeg

Sudo/Root Execution

Medium

Category: Privilege Escalation
Confidence: 70% confidence
Finding: Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
Content: Scanner excerpt · references/dependencies.md (reported line 21)May include surrounding context.
md
brew install ffmpeg # Ubuntu/Debian sudo apt update && sudo apt install -y ffmpeg # CentOS/RHEL sudo yum install -y ffmpeg

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The document instructs users to export a live API key and optionally persist it in ~/.openclaw/.env, but it does not warn that this credential is sensitive, should not be committed to source control, and should be protected with appropriate file permissions. This can lead to accidental credential disclosure through shell history, shared environments, backups, or checked-in dotfiles.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: All user-facing instructions in the file are presented only in Chinese, and there is no indication that the skill is region-specific or that users can opt into this locale. The policy requires flagging natural-language locale constraints when they force a specific language without user choice or clear justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file contains user-facing instructional text only in Chinese, which can constitute a language/locale policy issue when no user opt-in or alternative language option is provided. The file does not state that it is intended only for a Chinese-language audience or region-specific context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: Line L010 states that image prompts must be in English, which imposes a language requirement in natural-language guidance. The file does not offer opt-in, alternatives, or a documented justification for this locale/language constraint.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.