ClawHub
Back to skill

Security audit

Sites Friendify Integration

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent, but it can create live Docker/Traefik sites from a simple Telegram trigger without clearly requiring confirmation or defining operational safeguards.

Review this before installing if the agent has real Docker, Traefik, Telegram, or OpenClaw gateway access. Use it only where creating and deleting Friendify sites from user requests is intended, and require explicit confirmation before deployment, privacy changes, or deletion.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs the agent to deploy infrastructure and later allows deletion of managed sites, but it does not explicitly warn users that these actions create, modify, and destroy live system resources. In an agent context, missing disclosure around side effects can cause unintended operational changes, especially when a casual request triggers deployment and management actions tied to authenticated backend APIs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill defines the user request as the German phrase "erstelle seite" and repeats that exact trigger in the AI usage instructions. There is no indication that other languages are accepted, that the user can choose a locale, or that the German-only trigger is required for a region-specific reason.

Content

No source excerpt is available for this finding.