ClawHub
Back to skill

Security audit

Is Token Safe?

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but its advertised token-safety check is unreliable and may give users or bots a false sense of safety.

Review carefully before installing or using in any automated trading flow. The artifacts do not show credential theft, persistence, or destructive behavior, but the skill can fail open or understate token risk, so it should not be trusted to decide whether a token is safe without fixes and tests.

A.I.G

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 (3)

T09 · Insecure Skill Coding Practices

Error
Location
scan.js.js:92
Finding

Confirmed Honeypot Risk Is Incorrectly Downgraded

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scan.js.js:18
Finding

Contract Capabilities Are Falsely Inferred from a Locally Defined ABI

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
skill.json.txt:5
Finding

Configured Skill Entry Point Is Missing and the Available Handler Performs No Safety Scan

Content
View full analysis
Remediation
View remediation

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 (1)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scan.js.js (reported line 83)May include surrounding context.

js
try {
    const res = await axios.get(
      `https://api.honeypot.is/v2/IsHoneypot`,
      {
        params: {
          address: token,

Static analysis

No suspicious patterns detected.