azure-active-directory-b2c
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides numerous references to official documentation hosted on learn.microsoft.com and suggests the installation of tools from the MicrosoftDocs organization on GitHub. These are recognized as well-known and trusted services.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation from external URLs, which represents a potential surface for indirect instructions to be introduced into the agent's context.
- Ingestion points: Documentation content retrieved from learn.microsoft.com via the microsoft_docs_fetch or fetch_webpage tools.
- Boundary markers: The skill does not define specific delimiters or isolation instructions to separate fetched content from the agent's internal reasoning or system prompt.
- Capability inventory: The skill environment facilitates network access and file system reading as part of its primary function.
- Sanitization: No specific validation, filtering, or sanitization steps are implemented for the Markdown content retrieved from the remote documentation sources.
Audit Metadata