goal

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to embed the user-provided objective verbatim into CLI commands (okou goal create --objective "") and to echo the objective back to the user, so if the objective contains secrets (API keys, tokens, passwords) the agent would include those secret values verbatim in its output/commands, creating an exfiltration risk.