azure-iot-central
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation from
learn.microsoft.comthrough themicrosoft_docs_fetchandfetch_webpagetools. These requests target official Microsoft domains. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web pages.
- Ingestion points: Documented URLs from
learn.microsoft.comare fetched at runtime viamicrosoft_docs_fetchorfetch_webpage. - Boundary markers: None explicitly defined in the skill instructions to separate fetched content from internal instructions.
- Capability inventory: The skill utilizes tools to fetch and read web content as markdown.
- Sanitization: No explicit sanitization or filtering of external content is described.
Audit Metadata