data-quality-auditor

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (scripts/data_profiler.py, scripts/missing_value_analyzer.py, scripts/outlier_detector.py) to perform its primary function. These scripts are self-contained and do not perform any hidden or dangerous operations.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8).
  • Ingestion points: Data enters the agent context through the output of the provided Python scripts which read user-supplied CSV files.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore content within the processed data output.
  • Capability inventory: The skill has the ability to run local scripts and provide analysis results to the user; no network or high-privilege file system capabilities are present.
  • Sanitization: The scripts use standard CSV parsing and report raw cell values (e.g., in 'top values' sections), which could theoretically contain malicious instructions targeting the LLM if the dataset is attacker-controlled.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:06 AM
Security Audit — agent-trust-hub — data-quality-auditor