writing-style

Fail

Audited by Snyk on Mar 25, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 0.80). The prompt requires the agent to include verbatim excerpts from user-provided text and to read/merge files, so if those inputs contain API keys, tokens, or passwords the model would reproduce them in its output (exfiltration risk).

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Mar 25, 2026, 09:42 PM
Issues
1