v1.3.0

Unified Session — One Agent, All Devices, Zero Context Loss

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 7:54 AM.

Analysis

This instruction-only skill is coherent and purpose-aligned, but users should understand that it intentionally merges chat history across channels and persistently changes OpenClaw session routing.

GuidanceThis appears suitable for a personal single-user OpenClaw setup. Before using it, confirm no one else can DM your bot, back up the OpenClaw config, and understand that all selected channels will share one conversation history until you revert the setting.

Findings (2)

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.

Tool Misuse and Exploitation

SeverityLowConfidenceMediumStatusNote

SKILL.md

Edit `~/.openclaw/openclaw.json` ... `"session": { "dmScope": "main", "mainKey": "main" }` ... `openclaw gateway restart`

The setup requires local configuration changes and a gateway restart, which are expected for this skill but still change agent behavior.

User impactInstalling and using the skill can alter how OpenClaw routes and stores sessions across all enabled channels.

RecommendationReview the config change before applying it, back up ~/.openclaw/openclaw.json, and restart the gateway only when you are ready for all selected channels to share one session.

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

SeverityMediumConfidenceHighStatusNote

README.md

✅ **Shared memory** — your agent remembers everything, regardless of which app you used ... ⚠️ **Not for multi-user bots** — if multiple people DM your agent, keep sessions isolated to prevent context leakage.

The skill intentionally makes conversation memory shared across channels and explicitly warns that multi-user use could leak context.

User impactMessages from one channel can influence what the agent remembers and says in another channel; this is useful for a single user but unsafe if other people can DM the bot.

RecommendationUse only for a personal, single-user agent, and keep channel isolation enabled if any other person or shared account can message the bot.