ClawHub
Back to skill

Security audit

Pushbullet

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Pushbullet integration that discloses OAuth-based access, sending pushes, file pushes, chat/device management, and destructive actions without evidence of hidden or malicious behavior.

Install this only if you trust ClawLink with your Pushbullet OAuth connection. Use it for explicit Pushbullet tasks, review send/update/delete requests carefully, and remember that file pushes, links, notes, chat data, device identifiers, and push history may leave or be exposed through your Pushbullet account and related upload infrastructure.

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)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The skill description is broad enough to match common user intents around notifications, messaging, and sharing links or notes, which can cause the agent to invoke this integration in situations where the user did not clearly intend to use an external third-party service. In this context, that increases the chance of unintended data transmission to Pushbullet, especially because the skill supports cross-device messaging and sharing.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill advertises file sharing and cross-device transfer but does not prominently warn that file contents and metadata will be uploaded to external infrastructure, including signed upload URLs and Pushbullet/S3-backed storage. Users may assume a local device-to-device action when the workflow actually sends data to third-party services, creating confidentiality and privacy risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.