discovery-eyes

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill's output format requires quoting supplied sample messages verbatim and the required inputs explicitly accept "real (sanitized) or representative" messages, so if a user supplies samples containing API keys, passwords, or other secrets the LLM is instructed to reproduce them verbatim, creating an exfiltration risk.