dep-egress

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires quoting request payloads and "what is actually put in the body or query string" and even instructs to quote exact env vars/config from source, which forces the LLM to reproduce secret values (environment variables, tokens, keys, or hardcoded credentials) verbatim in its findings.