magic-data-synthesis

Warn

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/batch_synthesize.py employs the Python eval() function to execute logic defined in the expression strategy. Although it implements a basic sandbox by clearing __builtins__, this technique is frequently bypassable and represents a risk if the configuration containing the expression is sourced from an untrusted entity.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.
  • Ingestion points: Data is ingested from CSV, Parquet, JSON, and JSONL files via scripts/batch_synthesize.py and scripts/generate_column.py.
  • Boundary markers: The system uses standard string interpolation in synthesis_prompt_builder.py without robust separators to distinguish data from instructions.
  • Capability inventory: The skill can perform arbitrary Python execution (via eval() in batch_synthesize.py), shell command execution through the data-designer CLI, and network operations for LLM API calls.
  • Sanitization: Basic sanitization is performed in synthesis_utils.py (stripping newlines and truncating values), but it does not prevent the execution of malicious instructions embedded within the processed text.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 3, 2026, 07:00 AM
Security Audit — agent-trust-hub — magic-data-synthesis