ClawHub

Chaterimo

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Chaterimo integration that reads chatbot and customer-service conversation data using a user-provided API key.

Install this only if you are comfortable letting an agent read Chaterimo chatbot metadata and redacted customer conversation transcripts. Use a least-privilege or read-only API key if available, keep the key out of source control and shared logs, rotate it if exposed, and phrase requests with “Chaterimo” when you want this skill to access that account.

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 (2)

Missing User Warnings

Low
Confidence
83% confidence
Finding
The README instructs users to export a live API key into their shell environment but does not include any warning about keeping the credential secret, avoiding shell history leaks, or using secure secret storage in CI and shared systems. This is a real but low-severity documentation security weakness because users may copy the example into insecure contexts, accidentally expose the key in logs, screenshots, shared terminals, or persistent shell config files.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are very broad, natural-language requests such as "Show me all my chatbots" and "Show me conversations from last week," which overlap with ordinary user intents in many contexts. This can cause unintended invocation of the skill and expose business conversation data or metadata from the connected Chaterimo account when the user did not explicitly mean to access this integration.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal