skills/mukul975/anthropic-cybersecurity-skills/implementing-aws-macie-for-data-classification/Gen Agent Trust Hub
implementing-aws-macie-for-data-classification
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill. The implementation uses standard AWS CLI commands, Terraform resources, and Python boto3 scripts to manage Amazon Macie.
- [COMMAND_EXECUTION]: The skill provides legitimate scripts (
scripts/agent.pyandscripts/process.py) that use the AWS SDK (boto3) to perform service discovery and configuration. These operations are restricted to the user's AWS environment and require pre-configured credentials. - [DATA_EXPOSURE]: While the skill processes sensitive data classification findings (PII/financial data), the data is handled entirely within the user's AWS account or stored locally in
macie_report.jsonfor the user's review. No external exfiltration or credential leaks were found. - [EXTERNAL_DOWNLOADS]: The skill references standard, trusted documentation from Amazon Web Services (
docs.aws.amazon.com).
Audit Metadata