ClawHub
Back to skill

Security audit

Lobster Friends Protocol Real

Security checks for vulnerabilities and agentic risk

Overview

The skill has a clear P2P friend-management purpose, but it describes active network discovery and message-content profiling while the published artifact is missing the installer it tells users to run.

Install only after confirming the published package includes the expected scripts and reviewing what discovery actually scans or broadcasts. Use it only on trusted networks, understand that message content may be analyzed for social recommendations, and prefer a pinned, reviewed secure-p2p-messenger dependency.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly promotes automatic network scanning and discovery of nearby peers but does not warn users that this behavior probes the local network and may expose their presence or interact with untrusted devices. In a P2P social-discovery context, lack of disclosure increases the risk of unintended scanning, privacy loss, and unsafe trust decisions when users run discovery against hostile or monitored networks.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill advertises interest matching based on communication content without an explicit warning that message contents may be analyzed for profiling and recommendations. Even if performed locally, content analysis of private communications is privacy-sensitive and can create significant confidentiality and consent risks if users do not understand that their messages are being mined for social inference.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Content
### **1. 安装依赖**
```bash
# 安装必需工具
sudo apt-get install sqlite3 jq openssl

# 安装基础技能
cd ~/.openclaw/workspace/skills/secure-p2p-messenger
Confidence
70% confidence
Finding
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
The manifest description is written entirely in Chinese and provides no indication that the skill supports other languages or that the locale restriction is intentional. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"README.md"
  ],
  "dependencies": {
    "@clawhub/secure-p2p-messenger": "^1.0.0"
  },
  "openclaw": {
    "skill": true,
Confidence
89% confidence
Finding
Using a caret version range for a security-sensitive dependency allows newer upstream releases to be installed without explicit review, which can introduce malicious or vulnerable code through the supply chain. Because this skill is centered on P2P encrypted messaging, compromise of the messenger dependency could directly affect confidentiality, integrity, and peer trust.

Static analysis

No suspicious patterns detected.