skills/columnar-tech/skills/adbc/Gen Agent Trust Hub

adbc

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the dbc command-line tool using standard package managers such as uv, pipx, brew, and winget. These installations target the author's own infrastructure and established package registries.
  • [COMMAND_EXECUTION]: The skill provides shell commands for tool installation and driver management (e.g., dbc install sqlite). These are functional commands for the tool's intended purpose and do not involve unauthorized privilege escalation or suspicious behavior.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading data from external databases and Parquet files, which represents a potential surface for indirect prompt injection if the ingested data contains malicious instructions.
  • Ingestion points: Code examples in resources/languages/ for Python, JavaScript, Go, R, Rust, and C++ demonstrate querying databases and reading files like penguins.parquet.
  • Boundary markers: None are present in the provided examples to delimit data from instructions.
  • Capability inventory: The skill has the capability to execute shell commands for tool management and perform arbitrary database operations.
  • Sanitization: No data sanitization or instruction-filtering logic is included in the basic usage examples.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 06:52 PM