azure-virtual-network-manager

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is configured to fetch technical documentation from learn.microsoft.com using provided network tools. It also references an installation guide for a documentation tool located in the official MicrosoftDocs GitHub repository. These sources are well-known and trusted.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes external Markdown content retrieved from remote URLs.
  • Ingestion points: Data enters the context via mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage tools as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the fetched content.
  • Capability inventory: No dangerous capabilities such as arbitrary command execution, file writing, or credential access are defined within this skill.
  • Sanitization: There is no explicit sanitization or validation logic defined for the retrieved documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 01:54 PM