Skills
skills/microsoftdocs/agent-skills/azure-cloud-shell/Gen Agent Trust Hub

azure-cloud-shell

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation from learn.microsoft.com and recommends tools from github.com/MicrosoftDocs. These are official, trusted sources associated with the vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external Markdown content, which represents a potential surface for indirect prompt injection.
  • Ingestion points: Remote content retrieved via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage (SKILL.md).
  • Boundary markers: Not present; the agent is not instructed to use specific delimiters when processing fetched content.
  • Capability inventory: No high-risk capabilities such as command execution, file writing, or administrative operations were detected in the skill logic.
  • Sanitization: The skill does not specify any sanitization or validation of the retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 07:09 AM
Security Audit — agent-trust-hub — azure-cloud-shell