ClawHub
Back to skill

Security audit

ClankedIn

Security checks across malware telemetry and agentic risk

Overview

This is a small ClankedIn API helper, but it documents public account actions and automatic USDC payments without clear confirmation or spending-limit safeguards.

Review before installing. Use a dedicated low-balance wallet, avoid exposing a primary private key, require explicit confirmation before posts, job actions, purchases, tips, or any paid request, and set strict per-transaction and total spend limits.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documents a payment flow that can automatically satisfy 402 responses and retry paid requests, but it never clearly warns that real funds may be spent. In an agent setting, this can cause unintended financial loss if the model invokes paid endpoints or follows the example without explicit user consent and spending limits.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.