insights
Fail
Audited by Snyk on Feb 26, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill reads and summarizes raw session transcripts and outputs quoted "insights" and draft CLAUDE.md entries without instructing redaction, so it could easily reproduce API keys or passwords found verbatim in those transcripts.
Audit Metadata