azure-data-share
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from official Microsoft domains (learn.microsoft.com) and references a tool repository on GitHub (github.com/MicrosoftDocs/mcp). These are official resources from the skill author (microsoftdocs) and are treated as safe, representing standard functionality for a documentation assistant.- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests external data from web sources to provide answers.
- Ingestion points: Content is fetched from learn.microsoft.com via the mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage tools as instructed in SKILL.md.
- Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" wrappers for the fetched content.
- Capability inventory: The skill is limited to fetching and displaying documentation; it does not contain scripts with dangerous capabilities like subprocess execution or file system modification.
- Sanitization: No explicit sanitization or filtering of the fetched markdown is defined, as the source is an official, highly trusted documentation provider.
Audit Metadata