Alibabacloud Openclaw Ecs Dingtalk

• Outcome: Review
• Latest audit: May 29, 2026 · 8:37 PM UTC
• Version: 0.0.2

Overview

This skill is a disclosed Alibaba Cloud deployment guide whose main risks are expected cloud, credential, and remote-installation risks, not hidden or malicious behavior.

Install only if you intend to let an agent create Alibaba Cloud infrastructure for OpenClaw and configure DingTalk/Bailian credentials. Use a dedicated least-privilege RAM user or role, avoid FullAccess in production, review the remote OpenClaw and NodeSource install scripts before execution, monitor ECS/EIP and model usage costs, and rotate or revoke Bailian and DingTalk credentials when finished.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (4)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The manifest trigger list includes generic phrases such as "AI agent platform," "DingTalk integration," and "DingTalk smart assistant" without limiting context. These are broad enough to match many unrelated conversations, increasing the chance of unintended invocation for requests not specifically about deploying OpenClaw on Alibaba Cloud ECS.

External Script Fetching

Low

• Category: Supply Chain

Content

aliyun ecs RunCommand \
  --RegionId ${region} \
  --Type RunShellScript \
  --CommandContent "apt-get update -y && apt-get install -y git curl wget && curl -fsSL --connect-timeout 30 --max-time 300 https://deb.nodesource.com/setup_22.x | bash - && apt-get install -y nodejs && npm config set registry https://registry.npmmirror.com && node -v && npm -v" \
  --InstanceId.1 ${instance_id} \
  --Timeout 600 \
  --user-agent AlibabaCloud-Agent-Skills

• Confidence: 15% confidence
• Finding: curl wget && curl -fsSL --connect-timeout 30 --max-time 300 https://deb.nodesource.com/setup_22.x | bash

External Script Fetching

Low

• Category: Supply Chain

Content

- **Sensitive information masking**: Mask middle portion of passwords, keys, tokens, IPs, instance IDs (e.g., `ak****3d`, `i-bp1****7f2z`)
- **Input validation**: Reject shell special characters (`;`, `|`, `&`, `$`, backticks, etc.). Use parameterized API calls
- **Command injection prevention**: Encode sensitive values for Cloud Assistant RunCommand using base64
- **Network timeout**: All curl/wget operations must include `--connect-timeout` and `--max-time` parameters
- Execute steps in order; verify success after each step; inform user of current step
- If any step fails, ask user for confirmation before continuing
- Cloud Assistant `RunCommand` results: poll `DescribeInvocations` every 15+ seconds

• Confidence: 15% confidence
• Finding: wget operations must include `--connect-timeout` and `--max-time` parameters - Execute steps in order; verify success after each step; inform user of current step - If any step fails, ask user for con

Chaining Abuse

High

• Category: Tool Misuse

Content

aliyun ecs RunCommand \
  --RegionId ${region} \
  --Type RunShellScript \
  --CommandContent "apt-get update -y && apt-get install -y git curl wget && curl -fsSL --connect-timeout 30 --max-time 300 https://deb.nodesource.com/setup_22.x | bash - && apt-get install -y nodejs && npm config set registry https://registry.npmmirror.com && node -v && npm -v" \
  --InstanceId.1 ${instance_id} \
  --Timeout 600 \
  --user-agent AlibabaCloud-Agent-Skills

• Confidence: 90% confidence
• Finding: && curl -fsSL --connect-timeout 30 --max-time 300 https://deb.nodesource.com/setup_22.x | bash

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

Detected: suspicious.generated_source_template_injection

User-controlled placeholder is embedded directly into generated source code.

Critical

• Code: suspicious.generated_source_template_injection
• Location: SKILL.md:305