sqlserver-diagnostics

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill contains multiple SQL script blocks intended for execution against a Microsoft SQL Server instance. These queries target Dynamic Management Views (DMVs) such as sys.dm_os_wait_stats, sys.dm_exec_query_stats, and sys.dm_os_performance_counters to provide performance telemetry.
  • [DATA_EXFILTRATION]: While the queries retrieve metadata like login_name, host_name, and query_text (via sys.dm_exec_sql_text), this is standard diagnostic practice. There is no evidence of the data being sent to external third-party domains or unauthorized locations.
  • [PROMPT_INJECTION]: The skill monitors query text currently executing on the server, which serves as a potential surface for indirect prompt injection (where a malicious query string could influence the agent). However, the risk is mitigated as the skill lacks high-privilege capabilities such as network exfiltration or file system modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 06:57 AM
Security Audit — agent-trust-hub — sqlserver-diagnostics