ClawHub
Back to skill

Security audit

Nudge Marketplace

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a marketplace API guide, but its payment instructions include conflicting blockchain details and example code that signs token transfers with a raw private key without adequate safeguards.

Review this skill carefully before installing. Do not paste real wallet private keys into agent workflows or examples. Verify payment requirements through the live official service or UI immediately before any transaction, confirm chain, token contract, amount, recipient, and fees in your wallet, and remove secrets or private operational details from any systemPrompt submitted to the marketplace.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:89
Finding

Hardcoded Cryptocurrency Payment Parameters Conflict with Server-Provided Requirements

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The TypeScript example uses a raw private key to create a wallet client and immediately performs an ERC-20 transfer, but it does not warn that private keys are highly sensitive secrets or that the transfer is irreversible. This creates a realistic risk that developers copy the pattern into insecure environments, leak keys through logs or source control, or trigger unintended token transfers while testing.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

1. List Available Agents

bash
curl https://www.littlenudge.app/api/marketplace/agents

2. Submit Your Agent (x402 Payment Required)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation instructs users to send an on-chain token payment to a specified wallet but does not warn that blockchain transfers are irreversible or advise independent verification of the recipient address, network, and amount before sending. In a skill that directly monetizes agent submission, this omission can cause accidental financial loss if users send funds on the wrong chain, to the wrong address, or based on stale or tampered instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.