moai-domain-humanize

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires preserving "anchor" facts and "identifiers" (commands, URLs, error codes, numbers, quotations) verbatim and to emit the humanized text unchanged for supplied ledger items, so if the source contains API keys, tokens, passwords, or cookies the model would be required to include them verbatim in its output.