ClawHub
Back to skill

Security audit

wundervault-vault

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly discloses how agents use selected credentials through a local broker, with owner-controlled setup, permissions, and approvals.

Review the external package and installer before running administrator commands. Grant only the credentials and hosts needed, require approval for sensitive actions, and set payment limits. Separate agents with different trust levels into different operating-system accounts. This review assesses the skill instructions, not the external broker's security guarantees.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · INSTALL.md (reported line 19)May include surrounding context.

Linux:

bash
sudo sh "$(npm root -g)/@wundervault/mcp-server/packaging/install-daemon.sh"

Windows and macOS: wundervault.com/install.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · INSTALL.md (reported line 30)May include surrounding context.

Use the full paths the installer printed in its last step. They usually are:

bash
sudo /usr/bin/node /usr/bin/wundervault-agent --pair              # Linux
sudo /usr/local/bin/node /usr/local/bin/wundervault-agent --pair  # macOS

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · INSTALL.md (reported line 31)May include surrounding context.

bash
sudo /usr/bin/node /usr/bin/wundervault-agent --pair              # Linux
sudo /usr/local/bin/node /usr/local/bin/wundervault-agent --pair  # macOS

Full paths, because with sudo a bare name could be found in a folder your agents can write.

Static analysis

No suspicious patterns detected.