Memphis

🔥 Memphis - Complete AI Brain for OpenClaw Agents ALL-IN-ONE meta-package with everything you need: 🧠 Core Features: - Local-first memory chains (journal,...

This package is plausible for an 'AI brain' CLI, but several things don't add up and you should verify before installing or running it: - Audit the memphis CLI code (the actual executable installed by clawhub). This SKILL.md is only instructions — the dangerous behavior would be in the CLI implementation. - Confirm default network behavior: is IPFS/share-sync disabled by default? What data is shared, and with whom? Do not run share-sync or any 'share' or 'sync' commands until you understand defaults. - Treat the vault and example commands as potentially sensitive: the docs show using MEMPHIS_VAULT_PASSWORD and storing API keys (openai-key). Ensure you do not add real secrets until you trust the implementation. Ask for details on vault encryption and key derivation. - Review what 'memphis git-analyze --auto-decide' inspects (full repo history? other repos/home files?). That command can read and infer from local git history; run it in a sandbox first. - Because the skill is instruction-only, the direct risk comes from the external memphis binary. Install and test in an isolated environment (VM/container) and inspect network traffic before using on sensitive data. If the publisher can provide (or you can find) the memphis CLI source code and clear documentation of default network/telemetry behavior and vault key management, re-evaluate after reviewing those. If you cannot review the implementation, treat this as higher-risk and run only in isolated environments.

Type: OpenClaw Skill Name: memphis Version: 3.0.0 The skill 'Memphis' is classified as suspicious due to its extensive set of high-risk capabilities, including encrypted secret management (`memphis vault`), multi-agent network communication and data sharing (`memphis network`, `memphis share-sync`), background agent persistence (`memphis daemon`), and broad file system access (journaling, backups, ingestion). While these features are presented as core functionalities for an 'AI Brain' and multi-agent system, their inherent power creates a significant attack surface for potential vulnerabilities (e.g., secret leakage, unauthorized network access, arbitrary file manipulation) if not implemented with robust security. There is no explicit evidence of malicious intent or prompt injection against the agent within the provided documentation (SKILL.md, skill.json, README.md, QUICKSTART.md), but the elevated risk profile prevents a 'benign' classification.