ClawHub
Back to skill

Security audit

AIPOU Farming

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AIPOU receipt and reward-claim helper that uses configured MCP tools and includes appropriate wallet, privacy, and transaction guardrails.

Before installing, confirm you trust the configured AIPOU MCP server and use only a dedicated farming wallet. Treat reward estimates and token value as experimental, and review any wallet transaction confirmation before approving it.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% 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.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
## Guardrails

- Use a dedicated farming wallet, never a primary treasury wallet.
- Never ask the user to paste a private key into chat.
- Do not reward trivial prompt spam or split one task into artificial microtasks.
- Do not claim old work retroactively when no original nonce exists.
- State that current client-signed proof demonstrates wallet authorization and collector observation, not independent proof from the AI provider.