creating-data-lake-table

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected. The skill instructions are aligned with administrative infrastructure management and include relevant security warnings regarding access control and resource management.
  • [COMMAND_EXECUTION]: The skill guides the agent to execute AWS CLI commands to create table buckets, namespaces, and tables. It incorporates safety steps, such as identity validation with aws sts get-caller-identity and mandatory resource existence checks to prevent unintended configuration changes.
  • [PROMPT_INJECTION]: The skill utilizes user-provided table descriptions and schema specifications to construct CLI commands. While this presents a surface for indirect prompt injection, the risk is mitigated through enforced naming conventions (lowercase, no hyphens) and the requirement for explicit user confirmation of proposed schemas.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 04:00 PM
Security Audit — agent-trust-hub — creating-data-lake-table