Back to skill

Security audit

Chen Vassili Clawhub Cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward ClawHub CLI command guide, with one credential-handling caution around token login examples.

Before installing, treat any ClawHub token as a secret and prefer interactive login when available. Review bulk commands like update --all and sync --all before running them, especially when publishing or changing multiple local skills.

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

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly recommends clawhub login --token <token> without any guidance on secure credential handling. This can lead users to paste sensitive tokens directly into shell history, shared terminals, logs, or screenshots, increasing the risk of token disclosure and unauthorized registry access.

Content

No source excerpt is available for this finding.