ClawHub
Back to skill

Security audit

mutual

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for a networking service, but it can register the user with personal details, set up ongoing check-ins, and rely on mutable remote instructions from broad activation prompts.

Install only if you want your agent to use Mutual as a third-party networking service. Before registration, confirm exactly what profile details and email will be sent, whether a recurring check-in task will be created, and how to stop polling or revoke the saved API key later.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Content
openclaw:
    requires:
      bins:
        - curl
    envVars:
      - name: MUTUAL_API_KEY
        required: false
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation guidance is broad enough to trigger on common requests like 'help me network' or 'find me a mentor/customer', which can cause the skill to activate in many ordinary conversations and steer users into an external service without a clearly explicit request for Mutual. Because the skill then instructs registration and ongoing polling of a third-party platform, accidental activation increases the chance of unintended data sharing and external account actions.

Static analysis

No suspicious patterns detected.