candid-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires reading full project files and presenting offending code and concrete fixes (including showing code snippets) and explicitly flags "Hard-coded secrets or credentials" to be reported, but it gives no instruction to redact or avoid echoing secret values—so the LLM may be required to output secrets verbatim.