azure-virtual-machines
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a reference guide and does not include any executable scripts, obfuscated code, or persistence mechanisms. The functionality aligns with its stated purpose of assisting with Azure VM development.
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to fetch documentation from Microsoft's official Learn platform (
learn.microsoft.com). This is a well-known, trusted service providing technical documentation. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing external documentation content at runtime.
- Ingestion points: Documentation URLs defined in
SKILL.md,configuration.md,deployment.md, andintegrations.md. - Boundary markers: None provided; the skill does not specify delimiters or instructions to ignore embedded commands in the fetched data.
- Capability inventory: The skill does not contain local scripts, file-writing capabilities, or direct subprocess execution.
- Sanitization: No sanitization or filtering logic is defined for the external content before it is processed by the agent.
Audit Metadata