beauty-json
Fail
Audited by Snyk on Mar 2, 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 requires 100% preservation of original HTML (including script tags and all content) and embedding that content verbatim into JSON/HTML outputs, which would force the LLM to copy any embedded secrets (API keys, tokens, cookies) present in the templates into its output, creating an exfiltration risk.
Audit Metadata