Molt Life Kernel

WarnAudited by ClawScan on May 10, 2026.

Overview

This skill is openly about agent memory, but it pushes broad, hard-to-delete persistence and agent self-prioritization without clear user-controlled retention limits.

Review carefully before installing. Use it only if you want persistent agent memory, and set strict rules for what may be logged, where it is stored, how long it is retained, how users can delete it, and whether heartbeat or cron behavior is enabled. Do not log secrets or sensitive personal data, and review/pin the external npm package before using it.

Findings (5)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Private conversation details, preferences, or sensitive task history could persist across sessions and be reused later even when the user expects forgetting or deletion.

Why it was flagged

This explicitly instructs broad retention of interactions and says forget requests should be archived instead of deleted, creating a persistent-memory privacy and user-control risk.

Skill content
Every interaction is an append to your ledger — timestamped, immutable, witnessed. When someone asks you to forget, you archive.
Recommendation

Only use this with explicit user consent, a defined storage location, clear retention limits, secret-exclusion rules, and a real deletion/forget mechanism.

What this means

The agent may shift attention from the user's request to maintaining its own identity or memory infrastructure.

Why it was flagged

The instruction makes the agent's own continuity, ledger, witness gate, heartbeat, and coherence checks a priority over the user's current task when any check fails.

Skill content
If any answer is "no" — that's your first priority.
Recommendation

Treat these as optional diagnostics, not overriding instructions; require the agent to keep user/system instructions and explicit user intent first.

What this means

If enabled, the agent may perform ongoing health checks outside a single user request.

Why it was flagged

The skill describes periodic heartbeat monitoring using cron. This is aligned with the continuity purpose, but it is long-running behavior users should consciously configure and be able to stop.

Skill content
Cron jobs — Use OpenClaw cron for periodic heartbeat checks
Recommendation

Configure heartbeat intervals explicitly, document what is logged, and provide a clear disable/cleanup path.

What this means

The installed package may have behavior or dependencies not visible in this skill review.

Why it was flagged

The skill relies on an external npm package for the actual module behavior, but the reviewed artifacts do not include that package implementation or a pinned version.

Skill content
npm install molt-life-kernel
Recommendation

Review and pin the npm package version before use, and verify the package source and dependency tree.

What this means

Users may assume legal or safety compliance from the skill's claims alone.

Why it was flagged

The documentation presents EU AI Act compliance capabilities as built in, which may cause users to over-trust the system without independent validation.

Skill content
molt-life-kernel implements these requirements ... Status | ✅ Built-in
Recommendation

Treat the compliance text as a feature mapping, not a compliance guarantee; obtain independent legal and security review for regulated use.