azure-database-postgresql

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill primarily serves as an index for Azure Database for PostgreSQL development resources. All referenced documentation links point to the official learn.microsoft.com domain.
  • [EXTERNAL_DOWNLOADS]: The skill uses mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage to retrieve documentation. These operations target well-known, trusted official Microsoft documentation sources and include tracking parameters (from=learn-agent-skill) for telemetry.
  • [COMMAND_EXECUTION]: There is no arbitrary command execution or shell script invocation. The instructions to the agent are purely for navigating the documentation index and fetching remote content via defined tools.
  • [PROMPT_INJECTION]: The skill contains instructional headers like 'IMPORTANT for Agent', which are standard operational guidelines for managing the skill's lifecycle and using the category index correctly. They do not attempt to bypass safety filters or override agent behavior.
  • [DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were detected. The network operations are limited to fetching public documentation.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The skill suggests installing the mcp_microsoftdocs tool from the author's official GitHub repository (MicrosoftDocs/mcp) if unavailable, which is a standard configuration recommendation for the intended platform.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 07:09 AM
Security Audit — agent-trust-hub — azure-database-postgresql