azure-open-datasets
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
learn.microsoft.comand references an official Model Context Protocol (MCP) implementation atgithub.com/MicrosoftDocs. These are trusted sources and well-known services associated with the skill's author.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external documentation for development guidance.\n - Ingestion points: Documentation fetched via
microsoft_docs_fetchorfetch_webpage(SKILL.md).\n - Boundary markers: None explicitly provided in the skill instructions.\n
- Capability inventory: The skill uses file reading and network fetching capabilities to retrieve text.\n
- Sanitization: The instructions do not specify sanitization for the retrieved documentation content.\n
- Context: The ingestion of official documentation from trusted vendor infrastructure is a standard functional requirement and is considered safe.
Audit Metadata