special-category-data
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements logic for data classification based on standard GDPR Article 9 definitions. The provided Python script (
scripts/process.py) uses regex patterns to scan field names and sample values without performing any hazardous operations like network requests or unauthorized file access. - [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes field names and data samples provided by the user. However, the risk is negligible as the skill lacks dangerous capabilities such as file system writing, network exfiltration, or command execution.
- Ingestion points:
SpecialCategoryClassifier.classify_fieldinscripts/process.pyaccepts field names, descriptions, and sample values. - Boundary markers: No specific delimiters or "ignore instructions" prompts are used for the processed data.
- Capability inventory: The skill is restricted to classification logic and console reporting; no network or file-write tools are used.
- Sanitization: Input is processed via static regex matching, preventing executable code from being triggered.
- [COMMAND_EXECUTION]: No shell commands or dynamic execution patterns were identified in the instructions or scripts.
Audit Metadata