T09 · Insecure Skill Coding Practices
- Location
scripts/wan-video-gen.js:572- Finding
Configurable API endpoint can exfiltrate the DashScope bearer credential
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/wan-video-gen.js:572Configurable API endpoint can exfiltrate the DashScope bearer credential
Referenced artifact was not completely inspected
主要脚本:`node scripts/wan-video-gen.js`
Referenced artifact was not completely inspected
主要脚本:`node scripts/wan-video-gen.js`
Referenced artifact was not completely inspected
主要脚本:`node scripts/wan-video-gen.js`
Referenced artifact was not completely inspected
主要脚本:`node scripts/wan-video-gen.js`
Referenced artifact was not completely inspected
主要脚本:`node scripts/wan-video-gen.js`
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
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') {
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.
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.
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.
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.