edit

Fail

Audited by Snyk on Jun 27, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The Edit tool requires providing exact oldText/newText values (verbatim) for file changes, so the LLM may be forced to emit secret values (API keys, passwords, tokens) verbatim in its output, creating an exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Jun 27, 2026, 05:56 PM
Issues
1
Security Audit — snyk — edit