special-category-data
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a utility for privacy compliance and does not perform any network, file, or system operations.
- [SAFE]: The SpecialCategoryClassifier in scripts/process.py processes external data such as field names and sample values. This constitutes an ingestion point for untrusted data (Indirect Prompt Injection surface), but the script lacks any exploitable capabilities such as network access, filesystem writes, or command execution. Ingestion points: scripts/process.py (scan_system and classify_field methods). Boundary markers: Absent. Capability inventory: No subprocess calls, exec/eval, file-write, or network operations found in the codebase. Sanitization: Absent; the script uses regex for classification.
- [DATA_EXFILTRATION]: No logic for transmitting data to external servers or domains was found.
- [COMMAND_EXECUTION]: No shell commands or subprocess calls were detected in the provided scripts.
Audit Metadata