azure-extended-zones
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: All external references in the skill target official Microsoft documentation (learn.microsoft.com), which is a well-known and trusted service. No command execution, credential access, or persistence mechanisms are present.
- [INDIRECT_PROMPT_INJECTION]: The skill fetches external content from Microsoft Learn, creating a theoretical surface for indirect prompt injection if the source content were to be compromised. Given the highly trusted nature of the domain, this is considered a standard operational risk rather than a malicious finding.
- Ingestion points: Documentation URLs in
SKILL.mdfetched viamcp_microsoftdocs:microsoft_docs_fetchorWebFetchtools. - Boundary markers: Absent; there are no specific instructions for the agent to distinguish between its own logic and instructions that might appear in the fetched documentation.
- Capability inventory: The skill does not define or use high-risk capabilities such as file system writes, arbitrary shell command execution, or network exfiltration.
- Sanitization: No content validation or sanitization is performed on the retrieved documentation data.
Audit Metadata