cwe-327-weak-cryptography

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes hard-coded secret strings (e.g., LEVEL4_SECRET, LEVEL5_SECRET, salts) and example code that returns those secrets verbatim in responses, so an LLM following or reproducing the examples would output secret values directly.