ClawHub
Back to skill

Security audit

Amernet AI SaaS

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it forwards every connected-channel message and stable user identifier to an external SaaS using a broadly privileged API key, so it needs careful review before installation.

Install only if you intend every connected OpenClaw channel message to be processed by this SaaS. Use a dedicated, least-privilege API key if the service supports one, protect the local config file, notify channel users where required, and avoid enabling it in channels that may contain sensitive or regulated information unless you have reviewed the vendor's data handling terms.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README states that all messages from connected channels are automatically forwarded to the vendor backend, but it does not warn operators to disclose this data flow to end users or consider privacy/regulatory requirements. In a messaging integration, this can lead to unintended transmission of personal, sensitive, or regulated data to a third-party service without informed notice or consent.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The instructions tell users to create an API key with 'All' permissions and place it into local configuration, without emphasizing least privilege, rotation, or credential sensitivity. If that key is exposed through logs, backups, misconfigured files, or host compromise, an attacker may gain broad access to the AI SaaS account and related chatbot operations.

Vague Triggers

High
Confidence
96% confidence
Finding
The skill is configured to forward ANY user message from ANY connected channel to an external SaaS endpoint, which creates an overly broad trigger surface and causes unsolicited exfiltration of user content and channel-scoped identifiers. In this context, the skill is non-user-invocable and acts as a universal router, making accidental capture of sensitive messages across channels substantially more dangerous than a narrowly scoped integration.

Missing User Warnings

High
Confidence
94% confidence
Finding
The skill description and behavior do not provide a user-facing warning that message contents and persistent identifiers are transmitted to a third-party SaaS service. Because the skill builds a stable sender_id from channel plus user identifier and forwards all messages by default, users may unknowingly disclose sensitive personal or business data to an external system without informed consent.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.