remember
Fail
Audited by Snyk on Feb 22, 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 extracts and stores the "original text" as observations and echoes summaries/confirmations (and constructs memory JSON), so if a user-supplied secret is included it will be handled and output verbatim, creating an exfiltration risk.
Audit Metadata