literate-guide

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires the agent to read and emit verbatim code excerpts (with file/line ranges) from a codebase and does not instruct redaction, so any secrets hard-coded in the source or config would be reproduced in output, creating an exfiltration risk.