azure-blob-storage
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation content from official Microsoft Learn domains (learn.microsoft.com) and references a tool repository at github.com/MicrosoftDocs. These are recognized as trusted vendor resources.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests remote documentation content into the agent context. However, the risk is negligible due to the authoritative nature of the sources and the descriptive, non-executable nature of the content fetched.
- Ingestion points: Documentation content retrieved via
mcp_microsoftdocs:microsoft_docs_fetchorfetch_webpageas defined inSKILL.md. - Boundary markers: The skill does not define specific boundary markers for the fetched content.
- Capability inventory: The skill is designed for information retrieval and lacks capabilities for arbitrary command execution, file system modification, or network exfiltration.
- Sanitization: The skill relies on standard Markdown formatting for the retrieved documentation.
Audit Metadata