ClawHub
Back to skill

Security audit

Trace Stolen Crypto (MistTrack via Finch)

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a clearly scoped crypto-tracing workflow through named services, with explicit approval required for paid runs.

Your submitted address or transaction hash goes to Finch and MistTrack/SlowMist and may become associated with your account or inquiry. Share only identifiers you are comfortable disclosing. Confirm free-run availability, approve any charge explicitly, and never provide a private key or seed phrase. Tracing does not recover funds.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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 (1)

The workflow submits the user's wallet address or transaction hash to third-party services without a privacy warning.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The workflow instructs the agent to create a Finch task containing the user's input for MistTrack analysis. Although the providers are named, the skill does not warn that submitting an address or transaction hash discloses the user's investigation target to those services, potentially linking an otherwise public identifier to their account or inquiry.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.