ClawHub
Back to skill

Security audit

Jimeng Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Volcengine/Dreamina video-generation helper, with expected third-party API and credential use but no hidden code, persistence, or destructive behavior found.

Install only if you intend to use Volcengine/Dreamina cloud video generation. Treat prompts, uploaded images, and generated task data as being sent to a third party, keep the API credentials scoped and private, and watch for accidental activation from broad video-generation requests.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The README explicitly instructs users/agents to send content to an external API endpoint, which creates a real data egress path for prompts and possibly user-supplied creative content. In this skill's context that behavior is expected, but it is still security-relevant because users may unknowingly transmit sensitive material or use privileged credentials without clear disclosure.

Content

Scanner excerpt · README.md (reported line 31)May include surrounding context.

bash
# 生成视频
curl -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${API_KEY}" \
  -d '{

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The README documents use of a bearer token, references a local credentials file, and shows direct requests to a third-party API without any warning about secret handling, prompt/data disclosure, or log/shell history exposure. In an agent skill context, this can lead operators to expose API keys or unknowingly send sensitive prompts and media metadata to an external provider.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 65)May include surrounding context.

md
## 详细文档

查看完整文档：`~/.openclaw/skills/jimeng-video/SKILL.md`

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill explicitly instructs users to send prompts and generation requests to a third-party API, but it does not clearly warn that prompts, uploaded images, and related metadata may leave the local environment and be processed by an external provider. In a content-generation skill, this can expose sensitive business data, personal information, or proprietary media if users assume the tool is local or privacy-preserving.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
84% confidence
Finding

The documented curl command sends user-supplied content directly to an external endpoint using a bearer token, which creates a real data egress path to a third-party service. While this is expected for a cloud video-generation tool, it is still security-relevant because sensitive prompts or images could be transmitted off-platform without explicit user awareness or organizational approval.

Content

Scanner excerpt · SKILL.md (reported line 94)May include surrounding context.

生成带声音的视频

bash
curl -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer ${API_KEY}" \
  -d '{

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list contains multiple broad activation phrases like general video creation terms, which increases the chance of accidental invocation for common user requests. Because this skill uses required cloud credentials, accidental routing is more dangerous here than for a passive skill: it may lead to unintended external API calls, consumption of paid resources, and execution under privileged configuration without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrase at line 11 is a generic user intent for video creation, which can cause this skill to activate for broad, unrelated requests instead of only explicit requests for this specific tool. In an agent ecosystem, overly broad triggers can hijack routing, causing unintended API use, surprise execution, and exposure of configured secrets to workflows the user did not specifically intend to invoke.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

A fully Chinese-only skill description can constitute a language policy issue when it implicitly forces one language without user opt-in or justification. The file does not indicate that the skill is region-specific or provide an alternative language option.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.