The Agent Skills Directory

[SAFE]: The skill is a documentation index for Azure Enclave services and poses no security risk.\n- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill references a tool in the MicrosoftDocs GitHub organization and fetches documentation from learn.microsoft.com. These references target official vendor resources and well-known services and are considered safe.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external documentation data, which is a potential attack surface.\n
Ingestion points: The mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage tools mentioned in SKILL.md.\n
Boundary markers: The skill instructions do not define specific delimiters for the fetched external content.\n
Capability inventory: The skill acts as an information resource and does not possess high-privilege capabilities such as arbitrary command execution or file system modification.\n
Sanitization: No explicit sanitization or filtering logic is described in the skill body for the retrieved documentation content.

azure-enclave