remember

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). This skill instructs the agent to take arbitrary user-provided content and generate/save it verbatim into Markdown memory files (and confirm what was stored), so any API keys, tokens, or passwords included in the content would be output and persisted verbatim, creating an exfiltration risk.