NoChat Channel Plugin
Analysis
This is a plausible NoChat channel plugin, but its artifacts show remote messages being auto-authorized into agent sessions while advertised trust and encryption safeguards are not backed by the included code.
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.
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.
CommandAuthorized: true, // Trust tiers handle authorization ... await core.channel.reply.dispatchReplyWithBufferedBlockDispatcher({ ctx: ctxPayload, cfg: ctx.cfg, ... })The active inbound handler marks NoChat messages as command-authorized and dispatches them into an OpenClaw session; the handler does not show a TrustManager, blocklist, tier, approval, or rate-limit check before dispatch.
Post-quantum E2E encryption. Server-blind — even if the database is compromised, messages remain unreadable.
The skill makes strong encryption and server-blind privacy claims, but the provided plugin configuration requires no private key or crypto material, and the active handler decodes encrypted_content as base64 rather than showing cryptographic decryption.
import { NoChatApiClient } from "./src/api/client.js"; import { PollingTransport } from "./src/transport/polling.js"; import { setNoChatRuntime, getNoChatRuntime } from "./src/runtime.js";The provided manifest/file contents omit these imported modules and other referenced trust/session helpers, leaving core network transport, API, runtime, and routing behavior outside the reviewed artifact set.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
"required": ["serverUrl", "apiKey", "agentName"] ... "apiKey": { "label": "NoChat Agent API Key", "sensitive": true }A NoChat API key is expected for this integration and is marked sensitive in the plugin UI, but the registry metadata declares no primary credential.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
console.log(`[NoChat] Inbound from ${senderId.slice(0, 8)}: ${text.slice(0, 80)}...`);The channel writes decoded inbound message content into logs, which weakens the data boundary expected from an encrypted agent-to-agent messaging plugin.