Amernet AI SaaS

• Outcome: Pass
• Latest audit: May 28, 2026, 6:37 AM
• Version:
  1.0.0

Overview

This skill appears to be a transparent connector to an external AI chatbot, but it will send connected-channel messages and identifiers to that SaaS service.

Reasonable to install if you intend to route selected channel conversations through Salesbay AI SaaS. Limit which channels are connected, notify users where required, avoid forwarding sensitive or regulated data unless your agreements allow it, and store/rotate the all-permissions API key carefully.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README states that all messages from connected channels are automatically forwarded to an external SaaS chatbot, but it does not warn operators about privacy, consent, or data-handling implications. In a messaging integration context, users may unknowingly transmit personal, sensitive, or regulated data to a third party, creating privacy and compliance risk.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The instructions tell users to create an API key with 'All' permissions and provide no warning about least privilege, storage, or credential sensitivity. If that key is exposed through logs, config leakage, or host compromise, an attacker could gain broad access to the SaaS account and associated chatbot operations.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The skill is designed to intercept and forward ANY message from any connected channel to an external SaaS, which creates a broad data-exfiltration and unintended-activation risk. In this context, the danger is increased because user content and identifiers are automatically transmitted off-platform without any narrowing conditions, consent gate, or channel scoping.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill documentation does not warn that both message contents and persistent user identifiers are sent to an external SaaS, which can lead to uninformed disclosure of sensitive data. This is especially concerning here because the skill uses per-user session keys derived from channel and user identifier, increasing privacy and tracking implications across messaging platforms.

VirusTotal

64/64 vendors flagged this skill as clean.