azure-service-connector

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No security issues detected. The skill's behavior is consistent with its stated purpose of providing Azure Service Connector documentation.- [EXTERNAL_DOWNLOADS]: The skill utilizes the mcp_microsoftdocs:microsoft_docs_fetch tool and fetch_webpage to retrieve documentation from learn.microsoft.com. This is an official, well-known service from a trusted organization (Microsoft).- [PROMPT_INJECTION]: The 'IMPORTANT for Agent' sections contain legitimate instructional guidance for how the AI should navigate the content and does not contain patterns associated with instruction overrides or jailbreaking.- [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: External documentation fetched from learn.microsoft.com via mcp_microsoftdocs and fetch_webpage (SKILL.md).
  • Boundary markers: None identified in the prompt templates.
  • Capability inventory: No high-risk capabilities detected (no file system writes, no subprocess execution, no network operations to unknown domains).
  • Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:00 PM