Skills
skills/microsoftdocs/agent-skills/azure-managed-lustre/Gen Agent Trust Hub

azure-managed-lustre

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage to retrieve technical documentation from learn.microsoft.com. These references target official Microsoft documentation and are considered trusted sources.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: External documentation is dynamically fetched via specified tools as described in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or use 'ignore embedded instructions' warnings for the fetched content.
  • Capability inventory: The skill instructions (SKILL.md) allow the agent to use read_file to access parts of its own content.
  • Sanitization: There is no evidence of sanitization or filtering of the external documentation content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:41 AM