ClawHub
Back to skill

Security audit

Rebind Computer Use

Security checks for vulnerabilities and agentic risk

Overview

This skill is clearly meant for desktop automation, but it grants broad control over the user's computer through an unpinned downloaded MCP server.

Install only if you trust Rebind and the npm package source, and understand that this gives an agent powerful control over your active desktop session. Prefer a pinned, reviewed MCP server version and run it in a restricted account or sandbox when possible.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (2)

T08 · Insecure Dependencies

Error
Location
install.sh:25
Finding

Unpinned MCP Package Is Downloaded and Executed at Runtime

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:104
Finding

GUI Automation Server Exposes Excessive Host Capabilities

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is presented as a GUI-driving capability, but run_lua exposes far broader powers including system command execution, file access, network access, clipboard access, process control, and environment reads. That creates a large privilege expansion path where an agent can bypass GUI-only constraints, access sensitive local data, exfiltrate information, or perform arbitrary host actions under the guise of desktop automation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill states that execution APIs should only launch and manage applications, but elsewhere it explicitly encourages batching deterministic task steps into run_lua and documents powerful non-GUI namespaces. This inconsistency is dangerous because it creates a policy veneer of safety while still enabling agents to perform task logic directly through code, making misuse and policy bypass more likely.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · install.sh (reported line 18)May include surrounding context.

sh
# 2. copy the skill (this script lives alongside SKILL.md)
SKILLS="${OPENCLAW_HOME:-$HOME/.openclaw}/skills"
mkdir -p "$SKILLS/rebind-computer-use"
cp SKILL.md "$SKILLS/rebind-computer-use/"
echo "skill installed to $SKILLS/rebind-computer-use"

Static analysis

No suspicious patterns detected.