ClawHub
Back to skill

Security audit

Blockchain & DID

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent, but it can trigger identity verification and token staking actions without enough built-in warning or confirmation guidance.

Review this skill carefully before installing. It is not showing evidence of hidden code or local persistence, but it can guide an agent to perform sensitive blockchain-linked identity and token-staking actions. Only use it with a trusted API endpoint, and require clear user confirmation before KYC completion or token staking.

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
Confidence
89% confidence
Finding
The skill instructs the agent to drive users through on-chain KYC completion without requiring any explicit user-facing warning about privacy, identity verification consequences, or the permanence/sensitivity of submitted identity data. In a blockchain/DID context, this is materially risky because users may disclose sensitive personal information or trigger irreversible compliance/account-state changes without informed consent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The staking flow tells the agent to proceed from viewing tiers to staking tokens but does not require a warning that staking affects user assets, may lock funds, and may not be immediately reversible. In a blockchain membership system, omission of that warning can lead users to authorize financially consequential on-chain actions without understanding asset custody, lockup, or recovery implications.

Static analysis

No suspicious patterns detected.