write-script-mssql
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides standard developer instructions for using the wmill CLI and writing MSSQL queries. It emphasizes security best practices such as using parameterized queries to prevent SQL injection and explains how to safely handle external data from S3.
- [COMMAND_EXECUTION]: The agent is instructed to use the wmill toolset for operational tasks like previewing code, generating metadata, and syncing changes, which is appropriate for a development-focused skill.
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection via S3 objects.
- Ingestion points: S3 objects defined as parameters in SKILL.md.
- Boundary markers: None specified for query results.
- Capability inventory: Script execution via wmill CLI commands.
- Sanitization: Instructions clearly mandate SQL parameterization (@P1, @P2) to ensure data is handled safely, mitigating standard injection risks.
Audit Metadata