scope-check

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires the agent to "repeat the target contract in full, with the literal values, names, and numbers from the request" and to include literal values in done criteria, which would force the LLM to output any secret or credential the user supplied verbatim — creating an exfiltration risk.