Marrow

Persistent agent memory for OpenClaw. Surface past failures, log decisions, and compound intelligence across sessions. Use when an agent should enforce Marro...

This skill appears to do what it says (agent memory) but it mandates frequent logging to an external service and leaves redaction up to the agent. Before installing: 1) Confirm you trust getmarrow.ai and review their privacy, retention, and access policies; 2) Limit the MARROW_API_KEY scope where possible and use short-lived or revocable credentials; 3) Avoid enabling this skill in environments that handle sensitive PII, secrets, or regulated data unless you have contractual/data-residency guarantees; 4) Test in a sandbox with non-sensitive operations to verify what gets logged; 5) Consider monitoring outbound network calls and auditing logged memories on the Marrow side; 6) If you cannot guarantee safe redaction or vendor controls, do not enable mandatory automatic logging.

Type: OpenClaw Skill Name: marrow Version: 1.0.0 The skill provides instructions and a reference for using the Marrow MCP server to maintain persistent agent memory. It includes explicit safety guidelines in SKILL.md that forbid the logging of secrets, API keys, and PII, and it aligns perfectly with its stated purpose of improving agent decision-making through historical context. No malicious code, obfuscation, or unauthorized data exfiltration patterns were found.