Enables AI agents to grow organic personas through experience-driven memory with self-reflection and multi-layer persistent storage.

What to consider before installing/starting this skill: - The code implements a full local memory service (HTTP API, SQLite, markdown files, FAISS) and will create and modify files on disk. By default it writes under /root/.openclaw — review and change BASE_DIR before running if you don't want data in that path. - The HTTP API appears unauthenticated by default (ALLOWED_ORIGINS='*', API_KEY default empty) and the app binds to 0.0.0.0 by default; this can expose your data and endpoints to other machines. Do not run it on a network-exposed host without adding authentication and binding to localhost. - L1 uses Python pickle.loads when reading cached data. Pickle is unsafe for untrusted data because it can execute arbitrary code. Only run this service in a trusted environment and avoid feeding it untrusted serialized inputs. - ConfigSync can load arbitrary JSON/YAML files and will create personas from them; be careful not to point it to sensitive system files. Similarly, the service persists truncated content (e.g., L4 stores first 500 chars) which may include secrets — review retention/archival policies. - SKILL.md/README use different ports (9090 vs 8080) — double-check configuration before exposing the service. - Inspect requirements.txt and memory-manager.sh (not shown or truncated) before pip installing or running any startup scripts; FAISS and other binary packages can be heavy and may require special installation steps. Recommended actions: - Run in an isolated environment (VM, container) with controlled network access. - Change BASE_DIR to a non-root path you control and confirm permissions. - Set API_KEY and implement authentication or bind the service to localhost only. - Inspect memory-manager.sh and any omitted files for networking/backups before use. - If you prefer minimal risk, use a reviewed hosted memory API or a smaller, read-only instruction-only skill instead of running this code locally.

Type: OpenClaw Skill Name: dreammoon-memprocessor Version: 0.1.0 The bundle implements a sophisticated memory and persona management system but contains a critical security vulnerability in 'app/core/l1_storage.py' through the use of 'pickle.loads' for deserializing cached memory items, which presents a Remote Code Execution (RCE) risk. Additionally, 'memory-manager.sh' contains hardcoded absolute paths to the '/root/' directory and specific Conda environments, which is a poor security practice and suggests the script is tailored for a specific, potentially privileged environment. While 'app/services/event_detector.py' includes a security-positive feature to detect and de-prioritize sensitive data like GitHub tokens and OpenAI keys, the architectural flaws and unsafe serialization methods justify a suspicious classification.