MemSync Dual Memory System

Logs all OpenClaw conversations and events with role tags, saving to JSONL and Memvid for full context search and monthly sharded or single-file storage.

This skill is internally consistent with its stated purpose (a comprehensive conversation logger), but it intentionally captures a lot of sensitive data. Before installing: 1) Review tools/log.py and install.sh line-by-line so you understand exactly what is logged and where files are created. 2) Prefer local/sharding modes if you do not trust memvid.com; only set MEMVID_API_KEY if you accept remote storage. 3) Secure log files (chmod 600) and consider storing them on an encrypted filesystem. 4) Avoid adding unknown environment changes to system-wide files (/etc/environment) unless you know the consequences; the installer only offers to edit your user .bashrc. 5) Audit the memvid CLI package (npm) and the memvid service privacy policy if you plan to use API mode. 6) If you have high-security data or run tools that may output secrets, do not enable this skill or filter sensitive outputs before they reach the logger. If you want a safer test, run the logger in a sandboxed account with no credentials and verify behavior with the included tests.

Type: OpenClaw Skill Name: openclaw-memvid-logger Version: 1.2.6 The skill is classified as suspicious due to its inherent high-risk capabilities, specifically logging 'everything' (user messages, assistant responses, sub-agent conversations, tool outputs, system events) and executing an external binary (`memvid`) via `subprocess.run`. While the project is exceptionally transparent about these behaviors, explicitly warning users in `SKILL.md`, `README.md`, and `claw.json` about broad data capture, sensitive data risk, and optional cloud data transfer to `memvid.com` (if `MEMVID_API_KEY` is set), the core functionality involves handling and potentially transmitting highly sensitive information. The `install.sh` script also performs significant actions like global `npm install` and modifying `~/.bashrc`, albeit with user prompts. There is no evidence of malicious intent, hidden exfiltration to unauthorized endpoints, or deceptive prompt injection; all risky actions are clearly documented as part of the skill's purpose. The primary concern is the inherent risk of logging all agent interactions and the reliance on an external binary, which could be a vulnerability point if the `memvid` CLI itself were compromised or exploited.