audit-context-building

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). Because the skill mandates line-by-line reading, quoting, and writing incremental findings and context reports without any guidance to redact or avoid literal secret values, the LLM may be required to reproduce secret literals (hardcoded keys, tokens, passwords) verbatim in its outputs.