pii-masking-patterns
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICAL
Full Analysis
- EXTERNAL_DOWNLOADS (SAFE): The skill documentation references common Python packages such as 'llm-guard' and 'presidio-analyzer' (a Microsoft project). These are reputable tools for the stated purpose of PII protection.
- DATA_EXFILTRATION (SAFE): The skill is focused on preventing data exposure by providing masking logic for logging and observability. No indicators of unauthorized data collection or external transmission were found.
- SAFE (SAFE): Analysis of code snippets and documentation reveals no prompt injection, obfuscation, or persistence mechanisms. The automated scanner's detection of 'logger.info' is a false positive misidentifying a standard logging call.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata