learn

Fail

Audited by Snyk on Jul 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 instructs the agent to extract and POST conversation content (and then echo it back) verbatim to /api/learn, which means any user-supplied secrets, API keys, tokens, or passwords appearing in the thread could be copied into requests and responses — a direct secret-exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Jul 13, 2026, 04:51 AM
Issues
1
Security Audit — snyk — learn