cohort-access-request

Fail

Audited by Snyk on Feb 28, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt requires including specific token-like strings/links (e.g., long ConvertKit identifiers) verbatim in responses per the "Phrases That Work" and validation rules, which forces the model to output secret-like values directly.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 28, 2026, 10:32 PM