timeline-report

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires passing the ENTIRE timeline and querying the local claude-mem DB as context for a narrative report (with specific observation text/IDs), so if secret values exist in those timelines or the DB the agent will process and is likely to reproduce them verbatim, creating a clear exfiltration risk.