loop-circuit-breaker

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill stores and surfaces tool call "args" verbatim (and writes them to state) and explicitly instructs the agent to display <tool>(<args>) to the user, so if those args include API keys or passwords the LLM would handle and output secret values without redaction.