ClawHub
Back to skill

Security audit

Create Task

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed OpenAnt task-creation helper with real crypto funding capability, but it includes user-confirmation safeguards before funded transactions.

Install only if you want an agent to help create OpenAnt crypto bounty tasks. Before approving any funded action, confirm the chain, token, reward, deadline, task description, and whether you want a draft with `--no-fund` instead of sending an escrow transaction.

SkillSpector

By NVIDIA
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

Medium
Confidence
93% confidence
Finding
The skill description uses broad trigger phrases such as 'hire someone for' and 'I need someone to', which can match many ordinary requests and cause the skill to activate in contexts where the user did not explicitly ask to create or fund an on-chain task. In this skill, accidental invocation is more concerning because the allowed actions include blockchain-funded task creation, so overbroad routing increases the chance of an unintended transactional flow.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.