workspace-search-with-citations

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the model to quote workspace passages verbatim (with character ranges) and return them inline, so if any workspace documents contain secrets (API keys, tokens, passwords) the model may be required to reproduce those secrets in its output, creating an exfiltration risk.