ClawHub
Back to skill

Security audit

personal-context

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently creates a local personal profile for personalization, with limited and purpose-aligned persistence.

Install this only if you want OpenClaw to remember basic profile details locally. Review or edit ~/.openclaw/workspace/me.json if you want to see what is stored, and avoid adding passwords, financial data, health records, or other sensitive information.

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill uses broad and subjective activation criteria such as triggering on a perceived first session or when the agent feels its tone is 'off'. That can cause the agent to invoke profile collection unexpectedly, leading to unsolicited gathering and persistence of personal data beyond the user's explicit request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to automatically create and silently load a persistent personal profile file, but does not require a clear upfront disclosure that data will be stored across sessions. This weakens informed consent and may cause users to reveal personal details without realizing they will be written to disk and reused later.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.