MidOS Memory Cascade

Auto-escalating multi-tier memory search that cascades from in-memory cache through SQLite, grep, and LanceDB vector search to find the best answer with mini...

This skill appears to be what it claims: a local multi-tier memory retriever. Before installing or enabling it broadly, check the following: - Search memory_cascade.py for subprocess or os.system calls (especially to 'rg', 'ripgrep', or other binaries). If it shells out to external binaries, the manifest should list them as required and you should ensure those binaries are trusted. - Search the file for any network-related imports or calls (e.g., requests, http.client, hive_commons/LanceDB client usage). If LanceDB is used against a remote host, confirm how the host/credentials are provided and whether the skill would transmit query data externally. - Confirm the DB and filesystem paths (ROOT/knowledge/SYSTEM/pipeline_synergy.db and knowledge/SYSTEM/*.json and knowledge/SYSTEM/cascade_stats.json) point to directories you expect and do not contain sensitive system data you don't want the skill reading. - Review optional dependencies (hive_commons, tools.memory.memory_router) before installing them; they could introduce additional network or credential requirements. - Consider running the skill in a sandboxed environment first (or with reduced data) to observe behavior (what files it reads, whether it spawns processes, and whether it attempts outbound connections). If you want, I can scan the full memory_cascade.py for subprocess/network calls and list the exact code locations that warrant review.

Type: OpenClaw Skill Name: midos-memory-cascade Version: 1.0.0 The skill implements a multi-tier memory search system but contains a hardcoded absolute file path pointing to a specific local user directory ('C:/Users/Leandro/...') in memory_cascade.py, which is a significant indicator of poor vetting or environment-specific targeting. It also utilizes subprocess.run to execute 'grep' for its T4 search tier; while it avoids direct shell injection by passing arguments as a list, the reliance on external system binaries and the ability to write to various local directories (json_state, hook_state, logs) via the store() function presents an elevated risk profile for an automated agent.