microsoft-foundry-local
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from official Microsoft domains such as
learn.microsoft.comand thegithub.com/MicrosoftDocsorganization. These are recognized as trusted vendor resources. - [INDIRECT_PROMPT_INJECTION]: The skill is configured to fetch and process external data from the web using tools like
mcp_microsoftdocsorfetch_webpage. This capability introduces a surface for indirect prompt injection, where an agent could potentially be influenced by instructions embedded in the external content, although the referenced sources are highly reputable.
Audit Metadata