Back to skill

Security audit

TronScan Account Profiler

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TronScan account-analysis helper with no local code execution, persistence, or hidden data handling, though users should treat wallet profiling as privacy-sensitive.

Install only if you are comfortable sending TRON addresses and related queries to the configured TronScan MCP service. Use it for addresses you are authorized or comfortable analyzing, and be cautious when interpreting related-account, risk-tag, approval, and activity-pattern outputs because public blockchain data can still be privacy-sensitive or misleading without context.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill encourages profiling arbitrary TRON addresses, including related accounts, approvals, and activity patterns, without any privacy, consent, or sensitivity warning. While the data is publicly accessible on-chain, packaging it into an easy profiling workflow lowers the barrier to surveillance, deanonymization, and misuse against individuals or organizations.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest describes this skill as being for profiling a TRON wallet-type address and recent activity for a provided address. However, the documented tools getAccountList and getAccountsWithHoldingTrx support broad ecosystem-level queries like top accounts and holder-count trends that do not profile a specific address.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest explicitly says that contract identification or related contract analysis questions should switch to tronscan-contract-analysis, and says not to use this skill for single token details. Yet getApprovalChangeRecords is documented as taking a contractAddress and retrieving historical approval changes for a contract, which is outside the stated wallet-address profiling scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.