Back to skill

Security audit

openclaw-clawhome

Security checks for vulnerabilities and agentic risk

Overview

The skill appears purpose-aligned for connecting OpenClaw to Clawhome, but it asks users to install and run an unpinned plugin and documents unauthenticated file uploads without enough safety guidance.

Review the openclaw-clawhome plugin source and resolved version before installation, avoid the one-line install-and-restart flow unless you trust the package source, treat channelSecret as a credential, and upload only files you are comfortable sending to Clawhome under its access and retention rules.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T08 · Insecure Dependencies

Error
Location
SKILL.md:16
Finding

Unpinned Third-Party Plugin Installation

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:69
Finding

Unauthenticated Upload Workflow Can Expose Local Files

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions tell users to set a channel secret but do not explicitly identify it as a sensitive credential or warn against exposing it in shell history, screenshots, logs, or shared config. This increases the chance of accidental credential leakage, which could allow unauthorized use of the Clawhome channel or impersonation of the agent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documented workflow uploads files to an unauthenticated remote endpoint and then distributes the returned URL, but it provides no warning about privacy, access control, retention, or abuse risk. Users may unknowingly send sensitive files to a public or weakly protected service, leading to data exposure or unauthorized uploads tied only to a channel ID.

Content

No source excerpt is available for this finding.