pii-in-unstructured
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill implements PII detection logic using standard Python libraries and regular expressions.
- [EXTERNAL_DOWNLOADS]: The documentation references Microsoft Presidio and spaCy as recommended frameworks. These are trusted, well-known open-source libraries. The provided script does not initiate any downloads or installations.
- [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were identified. The logic focuses on local text processing.
- [COMMAND_EXECUTION]: There is no evidence of shell command execution, subprocess calls, or dynamic code evaluation.
- [PROMPT_INJECTION]: The skill instructions do not include any patterns designed to override agent behavior or bypass safety protocols.
Audit Metadata