plain-language

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the model to read project files and to include the quoted "original text" verbatim in findings, so any secrets accidentally present in reviewed prose could be reproduced in the output (the prompt only partially mitigates this by skipping some config items but does not guarantee exclusion of all secrets).