dont-to-do

Fail

Audited by Snyk on Apr 12, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The pipeline requires preserving the original input verbatim (writing it into the backfill JSON and emitting the refined query), so any secrets included in the user's input would be echoed back unless separately detected/masked, creating an exfiltration risk.

Issues (1)

W007
HIGH

Insecure credential handling detected in skill instructions.

Audit Metadata
Risk Level
HIGH
Analyzed
Apr 12, 2026, 06:36 AM
Issues
1