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 duckdb binary 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_auto and read_json_auto in SKILL.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
Risk Level
SAFE
Analyzed
Mar 24, 2026, 12:25 AM