azure-app-service
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch documentation content from the official Microsoft technical documentation site (
learn.microsoft.com). These references are directed to a well-known, trusted service. - [EXTERNAL_DOWNLOADS]: References an installation guide for a Model Context Protocol (MCP) tool hosted on the
MicrosoftDocsGitHub organization, which is a trusted repository associated with the skill's author. - [INDIRECT_PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection by fetching and processing external documentation content at runtime.
- Ingestion points: Document fetching is performed via the
mcp_microsoftdocs:microsoft_docs_fetchandfetch_webpagetools as described inSKILL.md. - Boundary markers: The skill does not explicitly define delimiters or specific "ignore embedded instructions" warnings for the fetched documentation content.
- Capability inventory: The skill itself does not include shell execution or file-write capabilities; it is focused on documentation retrieval and information synthesis.
- Sanitization: No specific sanitization or validation logic for the remote content is defined within the skill instructions.
Audit Metadata