hooks
Fail
Audited by Snyk on Mar 15, 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 reads .claude/settings.json and must preserve and write back all non-hook fields exactly, which forces the agent to read and re-output any secret values present in that file verbatim (exfiltration risk).
Issues (1)
W007
HIGHInsecure credential handling detected in skill instructions.
Audit Metadata