lf-new-feature

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires reading project inputs and producing a verbatim inventory and literal code/env-variable excerpts (including "chaves" and "variáveis de ambiente") into the generated briefing, which forces the LLM to reproduce any secret values present in those files verbatim.