code-chunker

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly reads and emits verbatim file sections (e.g., "Full content of lines 322-480" / "Read lines 87-145"), so if source files contain API keys, tokens, or passwords the LLM would be required to output those secret values verbatim, creating an exfiltration risk.