ClawHub
Back to skill

Security audit

Near Faucet

Security checks for vulnerabilities and agentic risk

Overview

This is a small NEAR testnet faucet helper with no hidden local access, though its documentation overstates status-checking and rate-limiting features.

Before installing, treat this as a simple testnet faucet requester and balance checker only. Do not rely on it to enforce rate limits or track request status unless those features are added elsewhere.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The skill documentation claims security-relevant behavior—status checking and rate limiting—that is not actually implemented. This can mislead users and downstream agents into relying on protections that do not exist, potentially enabling faucet abuse, failed operational assumptions, or unsafe automation decisions.

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The manifest description says the skill provides faucet requests, status checking, and balance queries with rate limiting. In this file, the implemented commands are only 'request' and 'balance', and there is no code that tracks request status or enforces any rate limit, creating a clear mismatch between claimed behavior and actual implementation.

Static analysis

No suspicious patterns detected.