azure-boards
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches remote documentation from
learn.microsoft.comand references theMicrosoftDocsGitHub repository. These are official, well-known resources managed by the vendor.- [INDIRECT_PROMPT_INJECTION]: The skill processes content fetched from external URLs, which represents a surface for indirect prompt injection. However, the ingestion points are restricted to trusted official Microsoft documentation domains, and the skill lacks high-risk capabilities like arbitrary command execution or sensitive local file access. - Ingestion points: Tools
mcp_microsoftdocs:microsoft_docs_fetchandfetch_webpageretrieve content fromlearn.microsoft.comas referenced inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined in the prompt instructions.
- Capability inventory: Capabilities are limited to documentation retrieval and display; no subprocess execution, file-write operations, or credential access patterns are present.
- Sanitization: No explicit sanitization or filtering of remote content is defined, relying on the source's integrity.
Audit Metadata