byted-bytehouse-data-quality-inspector

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The shell script scripts/export_config.sh uses the eval command to load environment variables parsed from a local JSON configuration file. While the script uses jq with the @sh filter to properly escape values, the use of eval on generated strings remains a sensitive execution pattern.
  • [PROMPT_INJECTION]: The skill processes external data (database schema and table data) to generate quality reports, creating a surface for indirect prompt injection where malicious database content could influence agent behavior.
  • Ingestion points: Schema metadata from system.columns and table content via scripts/inspector.py.
  • Boundary markers: None; the script does not use specific delimiters or instructions to ignore embedded commands in the data.
  • Capability inventory: Read-only database access via clickhouse-connect for executing statistical queries.
  • Sanitization: Database and table identifiers are interpolated into SQL queries using f-strings without additional sanitization or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:44 PM
Security Audit — agent-trust-hub — byted-bytehouse-data-quality-inspector