azure-iot
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches Azure IoT documentation from official Microsoft domains (learn.microsoft.com) using the provided tools. These references point to legitimate vendor-controlled infrastructure.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it retrieves and processes content from external web pages.
- Ingestion points: External documentation URLs listed in
SKILL.mdthat are retrieved viafetch_webpageormcp_microsoftdocs:microsoft_docs_fetch. - Boundary markers: None identified; the skill directly incorporates fetched Markdown content into the agent context.
- Capability inventory: No high-risk capabilities such as arbitrary command execution, file system writes, or network exfiltration were found in
SKILL.mdor its instructions. - Sanitization: No explicit sanitization or filtering of the retrieved content is mentioned.
Audit Metadata