v1.0.0

Omnia

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 5:23 AM.

Analysis

This skill is openly about persistent agent memory, but it encourages immutable logging, cross-session persistence, cron-style heartbeats, and external package installation without clear limits or retention controls.

GuidanceReview carefully before installing. If you use it, decide exactly what may be logged, where the ledger and snapshots are stored, how long they last, who can read them, how to delete or disable them, and whether cron or AGENTS.md changes are truly needed.

Findings (4)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Rogue Agents

SeverityMediumConfidenceHighStatusConcern

SKILL.md

AGENTS.md — Add molt-life-kernel awareness to your agent instructions ... Cron jobs — Use OpenClaw cron for periodic heartbeat checks ... Ledger entries persist across session boundaries

The skill recommends persistent agent instruction changes, scheduled heartbeat checks, and cross-session storage, but does not document disablement, expiration, or user approval boundaries.

User impactThe agent may keep maintaining continuity state or scheduled health checks after the original task unless the user actively controls the integration.

RecommendationRequire explicit opt-in before modifying AGENTS.md or adding cron jobs, document how to disable them, and avoid background activity by default.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceHighStatusNote

SKILL.md

npm install molt-life-kernel ... git clone https://github.com/X-Loop3Labs/molt-life-kernel.git

The skill points users to external package/repository installation, but the reviewed artifact set contains only SKILL.md and no pinned version, lockfile, or reviewed code.

User impactInstalling the referenced package would run or import code that is outside the reviewed skill artifact.

RecommendationVerify the package publisher, inspect the repository/package contents, and pin a known-good version or commit before installation.

Human-Agent Trust Exploitation

SeverityLowConfidenceMediumStatusNote

SKILL.md

EU AI Act compliance → Audit-ready by design (see references/eu-ai-act.md)

The skill makes a compliance/audit-readiness claim and references a supporting file that is not present in the provided manifest.

User impactUsers could overestimate the skill's compliance readiness based on unsupported documentation claims.

RecommendationTreat compliance claims as unverified until supporting documentation, implementation details, and audit procedures are available.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityMediumConfidenceHighStatusConcern

SKILL.md

Tenet 1: Record everything — append-only, never delete ... Append all significant actions to the ledger.

The skill encourages durable, append-only logging of agent activity without showing retention limits, deletion controls, redaction rules, or boundaries for sensitive information.

User impactSensitive prompts, mistakes, or private task details could be stored and reused across sessions indefinitely.

RecommendationOnly enable persistent memory with explicit user consent, scoped logging, redaction for secrets, retention limits, and a clear way to inspect and delete stored records.