azure-event-hubs
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches technical documentation from official Microsoft domains (learn.microsoft.com) and references the MicrosoftDocs MCP GitHub repository for installation instructions. These sources are verified and appropriate for the skill's stated purpose of providing Azure-related expertise.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external web pages. While fetching documentation from a trusted vendor is a standard functionality for this skill, the processing of external content creates an inherent surface for indirect prompt injection. The skill implements a best practice by including tracking parameters (e.g., from=learn-agent-skill) in its fetch requests.
- [SAFE]: The skill includes a conditional check on its own metadata (generated_at) to ensure the information provided to the user remains current. This is a legitimate maintenance feature and does not gate any security-sensitive operations.
Audit Metadata