sql-optimization
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions include a requirement for the agent to execute
mkdir -p .aixto ensure a specific directory exists before writing artifacts. This is a low-risk command used for project organization. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-selected code or queries via the
${selection}variable. - Ingestion points: Untrusted data enters the agent context through the
${selection}placeholder inSKILL.md. - Boundary markers: None are present to delimit the untrusted selection from the agent's instructions.
- Capability inventory: The skill includes instructions to execute shell commands (
mkdir) and perform file-writing operations to the.aix/directory. - Sanitization: No explicit sanitization or validation of the input selection is defined in the instructions.
Audit Metadata