correction-pipeline

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs embedding "verbatim, user's words" into CLI commands and gbrain remember/bootstrap calls (e.g. --set "corrected value" and gbrain remember "<...>"), which requires the LLM to output user-supplied values verbatim and thus could expose secrets if a user-provided correction contains credentials.