tsql-review

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a comprehensive set of 50 static analysis checks for T-SQL code. No malicious patterns, such as credential exfiltration, remote code execution, or unauthorized network access, were found.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: Raw T-SQL source code or .sql file content (SKILL.md). Boundary markers: None. Capability inventory: Static analysis and pattern matching of SQL constructs (SKILL.md); no execution capability. Sanitization: None. While the risk of following instructions embedded in SQL comments exists, the skill's restricted scope to analysis minimizes potential harm.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 11:13 AM