ClawHub
Back to skill

Security audit

Pushbullet

Security checks for vulnerabilities and agentic risk

Overview

The Pushbullet skill is mostly coherent and user-controlled, but its setup instructions include direct remote script execution that should be reviewed before installation.

Review the OOMOL CLI installer before running it, prefer a signed or checksum-verified installation path if available, and only approve Pushbullet write or delete actions after checking the exact target and payload.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
96% confidence
Finding

The skill instructs users to install the CLI by piping a remote script directly into a shell (curl ... | bash). This is a well-known unsafe pattern because any compromise of the hosting endpoint, TLS interception, DNS hijack, or malicious script update can immediately lead to arbitrary code execution on the user's machine. In this skill context, the risk is elevated because the installation command is presented as an approved recovery step for normal operation, making users more likely to execute it without verification.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

Static analysis

No suspicious patterns detected.