openclaw-memoryos-memory-admin

Inspect, back up, search, export, and update OpenClaw long-term memory stored with MemoryOS. Use when Codex needs to manage MemoryOS memory files for an Open...

This skill appears to be what it says: a local MemoryOS JSON admin tool. Before installing or using it, confirm the data_root you pass to the script points to the intended MemoryOS directory (to avoid accidental edits), and always run the provided backup command first. Review the bundled script if you can — it will create/overwrite long_term_user.json and long_term_assistant.json entries, set timestamps to 'now' for new entries, and deliberately writes empty 'knowledge_embedding' arrays for added items (which can temporarily degrade semantic search until embeddings are rebuilt by your runtime). If you want to limit autonomous changes, note that the skill metadata allows implicit invocation by the agent — consider disabling implicit/autonomous invocation for agents you don't trust or explicitly invoking the skill only when needed.

Type: OpenClaw Skill Name: openclaw-memoryos-memory-admin Version: 1.0.0 The skill bundle provides administrative tools for MemoryOS, but the core script `scripts/memoryos_admin.py` contains several security vulnerabilities. It lacks input sanitization for `user_id`, `assistant_id`, and the `--output` path, which could allow directory traversal or unauthorized file writes. Most notably, the `set-profile` command allows reading arbitrary local files via the `--profile-file` argument, potentially enabling an attacker to exfiltrate sensitive system data (e.g., `/etc/passwd`) into the MemoryOS JSON files. While these capabilities are aligned with the stated purpose of memory management, the lack of validation constitutes a significant vulnerability.