code-reader-v2-cn

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt forces agents to read actual project files and produce verbatim code excerpts and examples (including tokens/passwords shown in examples) and to write those contents into reports, which would require reproducing any secrets found in files and thus creates a high exfiltration risk.