Back to skill

Security audit

My Token Safety Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it checks BSC token risk by sending the provided contract address to GoPlus Labs and returns a risk summary.

Before installing, be aware that token addresses you check are sent to GoPlus Labs, so the service may see which contracts you are investigating and when. The skill is BSC-only and has Chinese runtime messages; it does not appear to access local files, credentials, or persistent system state.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (9)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's user-facing natural language is entirely in Chinese, including the description, prompts, and error messages. This imposes a specific language/locale on all users without any opt-in or alternative, which matches the language policy violation criteria.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill sends a user-supplied contract address to the external GoPlus Labs API without any user-facing notice or consent. Even if a contract address is public blockchain data, transmitting user queries to a third party leaks the user's interests, timing, and usage metadata, which is a real privacy issue in an agent context.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The code performs an external network transmission to a third-party service using user-provided input. In this skill's context, that transmission is expected for functionality, but it still creates privacy, dependency, and data-governance risk because user queries are exposed to an external operator without visible disclosure.

Content

Scanner excerpt · src/index.ts (reported line 18)May include surrounding context.

ts
function fetchTokenSecurity(address: string, chainId: string = '56'): Promise<TokenResult> {
  return new Promise((resolve, reject) => {
    const url = `https://api.gopluslabs.io/api/v1/token_security/${chainId}?contract_addresses=${address}`;
    https.get(url, (res) => {
      let data = '';
      res.on('data', chunk => data += chunk);

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 · dist/src/index.js (reported line 10)May include surrounding context.

js
function fetchTokenSecurity(address, chainId = '56') {
  return new Promise((resolve, reject) => {
    const url = `https://api.gopluslabs.io/api/v1/token_security/${chainId}?contract_addresses=${address}`;
    https.get(url, (res) => {
      let data = '';
      res.on('data', chunk => data += chunk);

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 · test.js (reported line 5)May include surrounding context.

js
function fetchTokenSecurity(address, chainId = '56') {
  return new Promise((resolve, reject) => {
    const url = `https://api.gopluslabs.io/api/v1/token_security/${chainId}?contract_addresses=${address}`;
    https.get(url, (res) => {
      let data = '';
      res.on('data', chunk => data += chunk);

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code includes natural-language strings in Chinese for errors and console output, which effectively forces a specific language for users. Under the policy, language-specific behavior should offer user opt-in or be clearly justified as locale-specific.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

Scanner excerpt · package.json (reported line 19)May include surrounding context.

json
],
  "license": "MIT",
  "devDependencies": {
    "typescript": "^5.4.0",
    "@types/node": "^20.0.0"
  }
}

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
40% confidence
Finding

Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.

Content

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

json
"license": "MIT",
  "devDependencies": {
    "typescript": "^5.4.0",
    "@types/node": "^20.0.0"
  }
}

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The error message is hard-coded in Chinese, and the rest of the skill's user-facing description and replies are also Chinese-only. This imposes a specific language on users without offering a language choice or documenting a justified locale restriction, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.