ClawHub
Back to skill

Security audit

beepctl

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Beeper messaging CLI skill, but it needs careful use because it can access chats, handle tokens, send messages, and save attachments.

Install only if you trust the external beepctl npm package and are comfortable letting an agent interact with Beeper-connected accounts. Never expose API tokens in transcripts or shell history, verify recipients and aliases before sending or archiving, require explicit confirmation before any account-changing action, and save attachments only to locations you choose deliberately.

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 (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is very broad and can match many ordinary requests about messaging, searching chats, or managing conversations across multiple platforms. In an agent environment, this increases the chance the skill is invoked in contexts where the user did not specifically intend to grant messaging-side effects, especially given the skill can send messages and manipulate chats.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
Documenting `auth show` and `auth set <token>` without a strong warning encourages handling API tokens directly in terminal history, logs, screenshots, or agent output. Because this skill controls unified messaging accounts, token exposure could allow unauthorized access to private messages and message-sending capabilities across connected platforms.

Missing User Warnings

Low
Confidence
76% confidence
Finding
The download feature writes attachments to local disk but does not warn about storing potentially sensitive content locally or overwriting files when an output path is chosen. In a messaging context, attachments may contain confidential documents or malware-laden content, so silent local persistence increases privacy and endpoint risk.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.