architect

Fail

Audited by Snyk on Apr 23, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires recording "ALL user input" verbatim into requirements.md (and to record references discovered during research into context-map.md), so any secrets the user or inspected code contains would be directly included in the agent's generated outputs.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 23, 2026, 02:26 PM
Issues
1