lakehouse-governance

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill focuses on security best practices, such as PII detection, data masking, and least-privilege IAM policy generation. No malicious patterns or security risks were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external table schemas and ETL code (Spark, SQL, dbt), which represents a potential surface for indirect prompt injection where malicious instructions could be embedded in metadata or code comments.
  • Ingestion points: Processes table schemas and ETL source code as described in SKILL.md.
  • Boundary markers: No specific delimiters or safety warnings are defined to isolate untrusted data.
  • Capability inventory: The skill has no capabilities for command execution, network access, or file system modifications.
  • Sanitization: No explicit sanitization or filtering of input data is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 02:53 AM
Security Audit — agent-trust-hub — lakehouse-governance