Back to skill

Security audit

wan-video-gen

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its video-generation purpose, but it can send a DashScope API key to any configured endpoint without validating that it is really DashScope.

Review this skill before installing. Use it only with a trusted config.json and environment, keep DASHSCOPE_BASE_URL unset unless you deliberately need a vetted DashScope endpoint, prefer storing the API key in environment variables rather than config.json, and expect successful runs to write MP4 files under outputs/ or the configured output directory.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/wan-video-gen.js:572
Finding

Configurable API endpoint can exfiltrate the DashScope bearer credential

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (10)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

md
主要脚本:`node scripts/wan-video-gen.js`

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 113)May include surrounding context.

md
主要脚本:`node scripts/wan-video-gen.js`

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.

md
主要脚本:`node scripts/wan-video-gen.js`

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.

md
主要脚本:`node scripts/wan-video-gen.js`

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 136)May include surrounding context.

md
主要脚本:`node scripts/wan-video-gen.js`

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · scripts/wan-video-gen.js (reported line 460)May include surrounding context.

js
if (args.duration !== undefined && requested !== rule.value) {
      throw new Error(`${model} 时长固定为 ${rule.value} 秒,不支持修改 --duration`);
    }
    return rule.value;
  }

  if (rule.type === 'enum') {

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill declares required environment access and clearly performs outbound API calls, but it does not explicitly declare a tool scope such as permissions or allowed-tools. This creates an authorization ambiguity where an orchestrator may grant broader capabilities than users expect, increasing the risk of secret exposure or unintended network actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The invocation description is broad enough that an agent may trigger this skill for loosely related requests involving video generation or task querying without clear boundaries. Over-broad routing can cause unintended external API calls, unnecessary spending, and use of sensitive prompts or credentials in situations where the skill was not actually appropriate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The operational instructions and policy-relevant guidance in this file are presented only in Chinese, with no indication that users may choose another language. The policy says to flag language or locale constraints when a skill forces a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation states that generated MP4 files are automatically downloaded to a local outputs/ directory, but it does not clearly warn users or downstream agents that invoking the skill causes a local file write. In an agent setting, implicit filesystem side effects can violate user expectations, create unwanted persistence of untrusted content, and increase the risk of accidental disk usage or unsafe handling of downloaded media.

Content

No source excerpt is available for this finding.