ClawHub
Back to skill

Security audit

Gougoubi Activate Created Conditions

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent but needs review because it can initiate live BSC mainnet staking and voting transactions from a user's wallet.

Review carefully before installing. This skill is meant for live crypto operations: it may ask your wallet to stake the minimum amount needed to join a Gougoubi proposal committee and then submit activation votes on BSC Mainnet. Only use it when you intend those on-chain effects, check the stake amount and gas before confirming in your wallet, and avoid automated use unless you add explicit stake/vote approval limits.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README describes a workflow that can automatically perform on-chain committee staking and activation voting, but it does not prominently warn users that the skill may spend funds and submit irreversible governance transactions. In an agent setting, this omission is dangerous because users or integrators may invoke the skill expecting read-only proposal processing while the agent actually joins a committee and casts votes on their behalf.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly allows auto-staking to join the committee if the wallet is not already a member, which is a wallet-affecting on-chain transaction with financial consequences. Although the skill says not to bypass wallet confirmation, it does not require an explicit user opt-in or prominent warning before initiating staking, creating a risk of unexpected asset commitment, fees, and mistaken authorization in an automated workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The boundary 'Keep Chinese user-facing errors concise and actionable' imposes a specific language for user-facing output. The file does not indicate user opt-in, language selection, or a documented region-specific justification for forcing Chinese responses.

Content

No source excerpt is available for this finding.