sql-gen
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
npxutility to download and execute theai-sqlpackage from the public npm registry. This introduces a dependency on external code from a source that is not verified as part of the author's primary infrastructure. - [COMMAND_EXECUTION]: The skill's core functionality relies on executing shell commands, specifically using
npxto run theai-sqlCLI tool with user-provided arguments. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) by interpolating untrusted natural language input into command-line arguments.
- Ingestion points: User-supplied descriptions passed as arguments to the
ai-sqlcommand (e.g., inSKILL.md). - Boundary markers: Absent; input is placed directly within shell quotes without specialized delimiters or instructions to ignore embedded commands.
- Capability inventory: Shell execution of the
ai-sqltool. - Sanitization: No sanitization or validation logic is present in the skill instructions to filter or escape the natural language input before execution.
Audit Metadata