ClawHub
Back to skill

Security audit

CAI: fund-agent-wallet-for-task

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped wallet-funding helper that creates a CAI hosted deposit link and does not include hidden code or automatic transfers.

Before installing, confirm you intend to use CAI hosted deposit links for an agent wallet and only provide a CAI API key you are comfortable using for that purpose. Review deposit links and balances before proceeding with any downstream payment task.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The 'When to Use' section lists natural-language trigger examples such as 'Fund my agent wallet so it can continue' and 'I need to top up before the agent pays' without clarifying negative examples or stricter activation constraints. These phrases are understandable but still broad enough that they could overlap with general payment-help requests, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.