self-reflection
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 skill requires reading and synthesizing ALL group and private chat logs and then writing them into diary/reflection outputs, which forces any secrets (API keys, tokens, passwords) present in those logs to be included verbatim in generated output, creating an exfiltration risk.
Audit Metadata