skills/damusix/skills/mssql-server/Gen Agent Trust Hub

mssql-server

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of 54 reference markdown files and a routing file. It serves as a pedagogical resource for SQL Server features ranging from basic DDL to advanced AI-driven features in SQL Server 2025.
  • [NO_CODE]: The skill does not include any executable scripts (.py, .js, .sh) or compiled binaries. It operates purely as a set of instructions and references for the agent to use when answering SQL-related questions.
  • [PROMPT_INJECTION]: No evidence of prompt injection, jailbreak attempts, or instructions to bypass AI safety protocols was found in any of the 55 files.
  • [DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive local file paths were detected. All code snippets involving configuration or credentials use standard documentation placeholders (e.g., 'YOUR_API_KEY_HERE', 'SecureP@ssword!').
  • [REMOTE_CODE_EXECUTION]: While the documentation covers features that interact with external services (like PolyBase for S3 or REST endpoint invocation), these are presented as T-SQL examples for the user rather than malicious instructions for the agent to execute unauthorized remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 09:27 AM