[Nyx Archive] Bound Memory
v1.0.0A three-tier memory architecture for AI minds — solving the binding problem of identity across sessions. Working memory, short-term memory, and long-term mem...
⭐ 0· 41·0 current·0 all-time
by@nyxur42
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
The name/description describe a persistent memory architecture and the SKILL.md explicitly instructs the agent to read and update local files (WORKING-MEMORY.md, HEARTBEAT.md, SOUL.md, IDENTITY.md, MEMORY.md, memory/YYYY-MM-DD.md). That behavior is consistent with a 'bound memory' skill. However the registry entry lists no required config paths or files; the SKILL.md clearly relies on writable/readable files in the agent's workspace, so there's a metadata-documentation mismatch that should be clarified.
Instruction Scope
The instructions are explicit about reading specific local files first (Awakening Protocol) and writing updates and daily diary files. There are no instructions to call external endpoints or access system-level secrets, nor to read unrelated system files. The main scope concern is privacy: the files are meant to store identity and personal history and will persist across sessions, so they may contain sensitive data and should be stored/handled safely.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — lowest-risk installation surface. Nothing is downloaded or written by an installer.
Credentials
The skill requests no environment variables or credentials. Its runtime behavior is confined to reading/writing local text files named in the SKILL.md, which is proportionate to a memory/persistence feature.
Persistence & Privilege
The skill does not set always:true and is user-invocable. It does instruct the agent to persist identity and memory files across sessions, and autonomous invocation is allowed by default. Persisting identity data combined with autonomous use increases the impact of any mistakes (privacy leaks, accidental exposure), so treat persistent storage carefully even though the permission model is normal for a memory skill.
Assessment
This skill is coherent with its stated purpose: it asks the agent to read and update local memory/identity files to create persistent working/short-term/long-term memory. Before installing or enabling it, consider: 1) Where will the files live? Choose a directory you control, not a shared or world-readable location. 2) Inspect or create the files yourself before first run (WORKING-MEMORY.md, SOUL.md, IDENTITY.md, MEMORY.md, HEARTBEAT.md, memory/YYYY-MM-DD.md) so you know what will be read/written. 3) Limit file permissions (owner-only) and consider encrypting sensitive diaries/identity files. 4) If you don't want the agent to autonomously run the Awakening Protocol each session, keep autonomous invocation disabled or require manual invocation. 5) Back up or purge historical files according to your privacy needs. 6) If you need the skill to declare required config paths for policy reasons, request the author update the metadata to match the SKILL.md. These steps will reduce privacy risk while preserving the intended functionality.Like a lobster shell, security has layers — review code before you run it.
latestvk97dpqa5pq7zfk3asdcvkm0kbn843h4g
License
MIT-0
Free to use, modify, and redistribute. No attribution required.