Skills
skills/microsoftdocs/agent-skills/azure-kubernetes-service/Gen Agent Trust Hub

azure-kubernetes-service

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation and configuration guidelines from official Microsoft domains and repositories.
  • The skill uses mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage to retrieve content from learn.microsoft.com.
  • It directs users to an installation guide for an MCP server hosted at github.com/MicrosoftDocs/mcp, which is a vendor-owned resource.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of ingesting external data.
  • Ingestion points: Remote documentation is fetched from learn.microsoft.com and processed by the agent in SKILL.md.
  • Boundary markers: There are no instructions for the agent to use delimiters or ignore instructions that might be embedded within the retrieved documentation.
  • Capability inventory: The skill utilizes read_file for local content and network fetch tools for remote documentation.
  • Sanitization: No sanitization or validation logic is defined for the content retrieved from external URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 10:24 AM