security-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires producing findings with a "vulnerableCode" field (and to report scanner/LLM findings by file:line), which will cause the model to include code snippets from the repo verbatim — including any API keys, tokens, or passwords found — so it forces potential secret exfiltration.