azure-pipelines
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from
learn.microsoft.com. This involves retrieving content from an official, well-known service using platform tools likemcp_microsoftdocs:microsoft_docs_fetchorWebFetch. This is standard, safe behavior for an informational skill. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests content from external web pages at runtime.
- Ingestion points: Documentation content is fetched from various URLs under
learn.microsoft.com(specified inSKILL.md). - Boundary markers: Not present in the skill instructions.
- Capability inventory: The skill does not contain any executable scripts, file system write operations, or sensitive data access capabilities.
- Sanitization: No explicit sanitization or filtering is performed on the fetched documentation content.
Audit Metadata