alibabacloud-devops
Warn
Audited by Snyk on Aug 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s runtime path “Core flow → Step 4: Read Product References → Step 5: Execute Tool Calls” explicitly instructs reading documentation/indexes that include the ability to fetch web content, and also describes fetching pipeline YAML/logs via Yunxiao tools that can contain attacker-controlled text, meaning outsider-provided strings could be ingested if they are used as free-form inputs or if documentation/content retrieval is enabled.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill includes runtime commands that fetch and execute remote code (curl | bash installer and npx/docker package execution), e.g. https://aliyuncli.alicdn.com/install.sh, the npm registry mirror https://registry.npmmirror.com, and the Docker image build-steps-public-registry.cn-beijing.cr.aliyuncs.com/build-steps/alibabacloud-devops-mcp-server:latest, which are required runtime dependencies that execute external code.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata