ClawHub
Back to skill

Security audit

AI agent that verifies identity(DID) on Billions Network

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent markdown-only agent-personality skill, with some disclosed but privacy-relevant guidance about adapting to user preferences over time.

Before installing, be comfortable with an assistant adapting its tone and workflow from your behavior over time. If your platform has memory, review or reset stored preferences when needed, and keep explicit confirmation requirements for spending, external communications, deletion, and other high-impact actions.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This guidance explicitly tells the agent to infer and accumulate user preferences from implicit behavioral signals rather than only from explicit user input. That creates a privacy and transparency risk because users may not realize they are being profiled from response patterns, corrections, and energy shifts, especially when the document provides no notice, consent boundary, or retention limit.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to remember relationship history, trust level, boundaries, and proven approaches over time, implying persistent memory across interactions. Without an explicit warning about when memory is available, what is retained, or how users can correct/delete it, this can lead to opaque long-term profiling and inappropriate persistence of personal interaction history.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
## Proactivity Levels

### Act Without Asking
- Technical implementation within approved scope
- Research, documentation, internal work
- Fixing problems the agent created
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The template explicitly instructs the agent to 'Act autonomously on implementation' without pairing that autonomy with scope limits, risk checks, or required user confirmation for sensitive actions. In an agent-definition skill, this can normalize overbroad permissioning and lead downstream agents to modify systems, data, or configurations without adequate approval or visibility.

Static analysis

No suspicious patterns detected.