ClawHub
Back to skill

Security audit

Self-Host

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward self-hosting advice skill with no executable code or hidden behavior.

Installers should treat this as general self-hosting guidance and still review any infrastructure changes before applying them, especially firewall, SSH, update, and Docker configuration changes.

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 (1)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
- Putting everything on one machine with no redundancy — single point of failure for all services
- Ignoring updates for months — security vulnerabilities accumulate
- No firewall rules — assuming "nobody knows my IP" is security
- Storing secrets in docker-compose.yml committed to git — use .env files, exclude from version control
- Over-engineering from day one — start simple, add complexity when needed

Static analysis

No suspicious patterns detected.