database-query
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes database CLI utilities such as psql, mysql, and mongosh via the Bash tool to manage connections, discover schemas, and run queries.- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from database query results, creating a risk that malicious content in the database could influence the agent.
- Ingestion points: Schema metadata and query results retrieved from connected databases.
- Boundary markers: No specific delimiters are defined to isolate database output from agent instructions.
- Capability inventory: Access to shell command execution (Bash), file writing (Write), and sub-agent tasking (Task).
- Sanitization: Lacks specific sanitization logic for data retrieved from the database before it is processed by the agent.- [DYNAMIC_EXECUTION]: The skill translates natural language into SQL/NoSQL strings which are then executed. It implements safety checks by requiring confirmation for write and schema modification operations.
Audit Metadata