anth-data-handling
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides functional Python code for PII redaction using regular expressions to mask SSNs, emails, phone numbers, and credit card numbers before data is sent to an external API.
- [SAFE]: Includes implementation for audit logging that explicitly avoids capturing PII or message content, following compliance best practices for data retention and access tracking.
- [SAFE]: The instructions encourage the use of least-privileged credentials, environment-specific configurations, and synthetic data for testing, which are standard security hardening techniques.
- [SAFE]: References to external resources (anthropic.com) are to well-known service providers relevant to the skill's stated purpose.
Audit Metadata