ClawHub
Back to skill

Security audit

Crypto Address Sentinel

Security checks for vulnerabilities and agentic risk

Overview

This is a simple wallet-monitoring skill whose webhook and address-tracking behavior match its stated purpose, though users should treat watched addresses as sensitive portfolio information.

Install only if you are comfortable configuring wallet addresses for monitoring. If you use `ALERT_WEBHOOK`, point it to an endpoint you trust because alert content may reveal portfolio associations and activity patterns. Use the short commands carefully, since they can list or change the watchlist.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises an ALERT_WEBHOOK for notifications but does not warn that monitored wallet balances and activity may be transmitted to an external endpoint. Even though blockchain data is often public, aggregating watched addresses and forwarding activity to a webhook can reveal sensitive portfolio associations, tracking behavior, and operational metadata to third parties.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The invocation example uses a very generic command, addresses, which can plausibly overlap with ordinary user language in a chat context and trigger the skill unintentionally. In a wallet-monitoring skill, accidental invocation could expose monitored address data, balances, or related activity when the user did not mean to access this capability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.