ClawHub
Back to skill

Security audit

Pushbullet

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Pushbullet integration guide, with account-changing powers disclosed, but it depends on an external ClawLink plugin and OAuth service that users must trust.

Install this only if you trust ClawLink and the clawlink-plugin source, because authorizing Pushbullet can permit reading account data and performing visible or destructive actions such as sending pushes or deleting pushes, chats, and devices. Prefer a pinned or verified plugin release if available, and review the OAuth scopes and confirmation prompts before approving write or delete actions.

A.I.G

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:36
Finding

Unpinned Third-Party Plugin Installation and OAuth Delegation

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md
## Authentication

Pushbullet uses OAuth 2.0 managed by ClawLink. No API keys are needed. Authorize access through the ClawLink dashboard. Your access token is stored securely and refreshed automatically.

Connect at: **https://claw-link.dev/dashboard?add=pushbullet**

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 78)May include surrounding context.

md
## Security & Permissions

- **Read** operations (listing devices, pushes, chats, user profile) are safe and require no confirmation.
- **Write** operations (creating pushes, chats, devices, updating settings) modify data and require confirmation.
- **Destructive** operations (deleting pushes, chats, devices, or clearing all pushes) are high-impact and irreversible.

Static analysis

No suspicious patterns detected.