azure-aks-edge-essentials
Warn
Audited by Snyk on Mar 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires runtime fetching of Markdown from Microsoft Docs (e.g., https://learn.microsoft.com/en-us/azure/aks/aksarc/aks-edge-troubleshoot-overview) via the mcp_microsoftdocs:microsoft_docs_fetch tool or fetch_webpage, which will be injected into the agent's context and therefore can directly control prompts.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 0.80). Flagged because the skill contains numerous administrative operations and PowerShell cmdlets (install/uninstall, start/stop VMs, create clusters/nodepools, configure SSH keys, set multiple administrators, update certificates, etc.) that would change the host system state and generally require elevated privileges.
Audit Metadata