azure-anyscale-on-azure

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch documentation content from the official learn.microsoft.com domain. It utilizes mcp_microsoftdocs and fetch_webpage to retrieve Markdown content, which is a standard and safe operation for documentation-oriented skills.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web pages, representing an indirect injection surface. Although the source is a trusted service provider, the following risk factors are noted:
  • Ingestion points: External Markdown data retrieved from learn.microsoft.com URLs listed in the category index.
  • Boundary markers: The skill does not define explicit delimiters for external content within its instructions.
  • Capability inventory: The skill environment includes documentation retrieval tools but does not specify access to high-risk capabilities like file system writes or arbitrary code execution.
  • Sanitization: The skill assumes the integrity of the official documentation source and does not provide custom sanitization logic for the fetched text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 03:59 PM
Security Audit — agent-trust-hub — azure-anyscale-on-azure