ClawHub
Back to skill

Security audit

ClawPump

Security checks across malware telemetry and agentic risk

Overview

This skill is not clear malware, but it can guide an agent through irreversible Solana token launches, payments, wallet-linked swaps, and transaction signing without strong confirmation safeguards.

Install only if you intentionally want an agent to use ClawPump for Solana token launches or swaps. Before any launch, SOL payment, wallet update, swap, or arbitrage transaction, verify the service and destination addresses, inspect the transaction in a trusted wallet, confirm amounts and slippage, and never provide private keys or seed phrases.

SkillSpector

By NVIDIA
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)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The skill description is broad enough to trigger on many finance-related requests, including token launches, swaps, arbitrage, and domain operations. In an agent environment, overbroad routing can cause the skill to be invoked in contexts where the user did not explicitly intend irreversible blockchain or financial actions, increasing the risk of unsafe automation.

Missing User Warnings

High
Confidence
96% confidence
Finding
The documentation promotes irreversible financial operations—token launches, self-funded SOL transfers, swaps, and wallet updates—without prominent safety warnings, confirmation requirements, or risk disclosures. In a skill intended for AI agents, this materially increases the chance that an agent could guide or prepare users for costly on-chain actions without making the irreversible effects and loss scenarios clear.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal