ai-redacting-data

Fail

Audited by Snyk on May 13, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill asks an LM to return detected entity "value" strings and the module records/prints an entities_found map containing original sensitive values (SSNs, credit cards, MRNs, names, etc.), which requires the LLM to output sensitive data verbatim and creates an exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
May 13, 2026, 06:46 PM
Issues
1