ClawHub
Back to skill

Security audit

TronScan Data Insights

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed TRON analytics helper, but it includes an address-level cross-chain lookup that conflicts with its stated non-profiling scope.

Install only if you are comfortable with the skill being able to route single TRON addresses to TronScan for cross-chain lookup; for aggregate network dashboards it is otherwise narrowly documented and does not include local code or persistence.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill manifest explicitly says it must not be used for single address profiling, yet the documented toolset includes getMultipleChainQuery, which performs direct address-level cross-chain lookup. This creates a scope-control failure: an agent could still use the skill for individual address investigation despite the stated restriction, enabling unintended deanonymization or profiling workflows.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

A single-address cross-chain mapping function is inconsistent with a network-insights skill intended for aggregate TRON activity, and it materially expands the capability surface into user/address attribution. If invoked inappropriately, it can be used to correlate identities or track entities across chains, which is more sensitive than the rest of the aggregate-statistics toolset.

Content

No source excerpt is available for this finding.