memory-management

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt repeatedly instructs the agent to store, reinsert, summarize, and display memory.content verbatim (e.g., into LLM prompts, context, and "Show me your memory"), so any API keys/passwords or secrets present in memory would be exposed to and potentially emitted by the LLM.