Back to skill

Security audit

Skills

Security checks for vulnerabilities and agentic risk

Overview

This DeFi skill is not obviously malicious and avoids private keys, but it needs Review because its helper can use arbitrary RPC endpoints that could mislead financial checks.

Install only if you are comfortable with a DeFi skill whose safety checks depend on the calling agent and wallet runtime. Use trusted RPC endpoints, require fresh simulation and explicit wallet confirmation before any transaction, avoid giving agents withdrawal authority, and consider pinning dependencies before production use.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
index.js:133
Finding

Unrestricted and Unverified RPC Endpoint Enables SSRF and Blockchain State Spoofing

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill description claims high-level Rerange order management, but the documented helper only exposes low-level deployment lookup, ABI dumping, calldata encoding, and arbitrary read calls. This mismatch can mislead an agent into trusting that the skill performs safety checks, previews, and constrained protocol-specific actions when it actually provides generic blockchain introspection primitives that may be used outside the stated safety model.

Content

No source excerpt is available for this finding.

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 320)May include surrounding context.

md
## Do Not

- Do not request or store private keys.
- Do not ask users to delegate unlimited wallet authority.
- Do not call vault `withdraw` from an automation agent.
- Do not use arbitrary vault `call` unless the owner explicitly requested the
  exact target, value, calldata purpose, and risk.

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 · vault-manager.md (reported line 113)May include surrounding context.

md
## Do Not

- Do not request or store private keys.
- Do not ask users to delegate unlimited wallet authority.
- Do not call vault `withdraw` from an automation agent.
- Do not use arbitrary vault `call` unless the owner explicitly requested the
  exact target, value, calldata purpose, and risk.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
93% confidence
Finding

The dependency on "viem" uses a caret range (^2.47.0), which permits automatic installation of newer minor and patch releases. This weakens build reproducibility and increases supply-chain risk because a compromised or breaking upstream release could be pulled in without explicit review. In a DeFi transaction-building skill, dependency integrity matters because library behavior can affect signing, transaction construction, and user fund safety.

Content

Scanner excerpt · package.json (reported line 20)May include surrounding context.

json
},
  "dependencies": {
    "@rerange/wagmi": "0.0.9",
    "viem": "^2.47.0"
  },
  "keywords": [
    "openclaw",