azure-sre-agent

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill contains numerous links to documentation hosted on learn.microsoft.com. These are official resources for Microsoft Azure services and are handled as safe references.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a mechanism for the agent to ingest external content via fetch_webpage or mcp_microsoftdocs.
  • Ingestion points: External documentation URLs in SKILL.md processed by fetch_webpage or microsoft_docs_fetch.
  • Boundary markers: None explicitly defined in the instruction text, though the agent is instructed to expect Markdown.
  • Capability inventory: The skill itself does not perform file writes, subprocess execution, or arbitrary network operations beyond fetching documentation.
  • Sanitization: Not explicitly defined within the skill content.
  • [SAFE]: The skill author microsoftdocs and the referenced resources are consistent with official Microsoft documentation workflows. The usage of MCP tools for fetching documentation is a standard integration pattern for this platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 07:03 AM