duckdb-en
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: Provides detailed instructions and examples for executing shell commands using the
duckdbbinary to query and transform local data files. - [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data files (CSV, Parquet, JSON), which represents a potential surface for indirect prompt injection.
- Ingestion points: Processes data from external files using functions like
read_csv_autoandread_json_autoinSKILL.md. - Boundary markers: Lacks specific delimiters or instructions to isolate data content from the agent's logic.
- Capability inventory: Includes shell command execution and file system write operations via the DuckDB CLI.
- Sanitization: Does not specify data validation or sanitization routines for the contents of processed files.
Audit Metadata