azure-confidential-ledger
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation content from the official Microsoft domain
learn.microsoft.com. This is a standard and expected operation for a documentation-focused knowledge skill using trusted sources. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data which represents a potential attack surface for indirect prompt injection.
- Ingestion points: External content is ingested from several
learn.microsoft.comURLs using tools likemcp_microsoftdocs:microsoft_docs_fetchorWebFetch(as defined inSKILL.md). - Boundary markers: The skill lacks explicit instructions or delimiters to warn the agent against executing or obeying potential instructions embedded within the fetched documentation.
- Capability inventory: This is a knowledge-base skill that primarily provides instructions for manual configuration and deployment; it does not include its own executable scripts or commands.
- Sanitization: There are no sanitization or filtering mechanisms described for the external documentation content.
Audit Metadata