explore-data

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides procedural instructions for an AI agent to perform data profiling, including schema discovery and statistical analysis.
  • [SAFE]: No network exfiltration, hardcoded credentials, or malicious persistence mechanisms were detected.
  • [SAFE]: The skill relies on standard SQL queries for database exploration and does not attempt to execute arbitrary or elevated system commands.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests external data from databases and files. However, the risk is negligible as the instructions focus on structural and statistical profiling.
  • Ingestion points: Data enters the context from user-provided files (CSV, Excel, Parquet, JSON) or connected warehouse tables (SKILL.md).
  • Boundary markers: No specific delimiters or instruction-bypass warnings are defined for the ingested data.
  • Capability inventory: Metadata querying and data reading for profiling purposes.
  • Sanitization: No explicit sanitization or filtering of the dataset content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:22 PM
Security Audit — agent-trust-hub — explore-data