value-dividend-screener

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt both instructs the agent to ask the user for API keys and includes examples that embed keys in commands (e.g., passing keys as CLI args or copy/paste export lines), which can require the LLM to include secret values verbatim in generated output and thus presents a high exfiltration risk.