english-proofreading

Fail

Audited by Snyk on Mar 6, 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 explicitly requires echoing the user's original English text verbatim in the "Original" correction block (and may reproduce secrets in the corrected/natural outputs), so any API keys/passwords included by the user would be output by the LLM — creating an exfiltration risk.
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 6, 2026, 06:34 AM