Back to skill

Security audit

AlibabaCloud Global Search

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill helps answer Alibaba Cloud product questions from official public sources and does not show hidden execution, persistence, credential theft, or account-changing behavior.

Installers should expect this skill to guide agents toward public Alibaba Cloud websites and to produce bilingual product documentation summaries. Review generated API or CLI snippets before use, especially cloud resource creation or deletion examples, and provide real credentials only in trusted, user-directed workflows outside the skill itself.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

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 · SKILL.md (reported line 1137)May include surrounding context.

  • 工单支持: 阿里云控制台提交工单
text

### Output Guidelines

1. **Prioritize based on user query**: Focus on sections most relevant to the user's question
2. **Use tables for structured data**: Specifications, pricing tiers, parameters, comparisons

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 647)May include surrounding context.

md
| **API Reference** | `https://www.alibabacloud.com/help/en/[product-code]/api-reference` | API documentation |
| **SDK Reference** | `https://www.alibabacloud.com/help/en/[product-code]/sdk-reference` | SDK guides |
| **Terraform Registry** | `https://registry.terraform.io/providers/aliyun/alicloud/latest/docs` | Terraform provider |
| **OpenAPI Explorer** | `https://api.alibabacloud.com/?product=[ProductCode]` | Interactive API testing |

### 3.9 常见问题文档来源 (FAQ Sources)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instruction explicitly requires 'Bilingual headers' for section titles, which imposes a language/locale choice on every response regardless of the user's preferred language. This is a natural-language policy issue because the skill forces a specific output language format instead of offering or inferring user-preferred language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file consistently presents user prompts, workflow guidance, and output examples primarily in Chinese, which can impose a specific language on users. Under the policy, locale or language constraints should either be optional or clearly justified; no such opt-in or justification appears here.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 639)May include surrounding context.

参考文档 (Reference Documentation)

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · examples.md (reported line 451)May include surrounding context.

参考文档 (Reference Documentation)

text

Static analysis

No suspicious patterns detected.