azure-defender-for-iot
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches content from the official Microsoft documentation domain (
learn.microsoft.com) using dedicated tools. This is the primary function of the skill and targets a well-known, trusted service. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface because it ingests data from external URLs at runtime.
- Ingestion points: External content is retrieved via
mcp_microsoftdocs:microsoft_docs_fetchorfetch_webpagefrom thelearn.microsoft.comdomain as specified inSKILL.md. - Boundary markers: None identified in the skill instructions to separate fetched content from system instructions.
- Capability inventory: The skill is restricted to documentation retrieval and does not possess capabilities for file modification, command execution, or network exfiltration to untrusted domains.
- Sanitization: No explicit sanitization or validation of the fetched markdown content is performed by the skill itself.
- Risk assessment: While the surface exists, the risk is negligible as the target source is an authoritative, trusted vendor (Microsoft), and the skill lacks dangerous execution capabilities.
Audit Metadata