ClawHub
Back to skill

Security audit

Nodit Web3 Data API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed read-only helper for querying Nodit Web3 data, with the main considerations being third-party API use and local UXC auth/link configuration.

Before installing, be comfortable configuring a Nodit API key in UXC and sending wallet addresses, contract addresses, chain/network names, and lookup inputs to Nodit. Prefer the packaged schema or a pinned schema source if you want tighter reproducibility, and keep use to the documented read-only operations.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
The declared description says the skill operates the Nodit Web3 Data API via UXC with a curated schema and guardrails. However, this code chunk does not perform API access, UXC linking/execution, or Web3 data reads. Its sole behavior is local static validation of the skill package contents and required strings/schema elements. That is a materially different primary purpose from the declared runtime functionality, so this is a description-behavior mismatch.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill instructs users to configure API-key auth and send requests to `web3.nodit.io` and `raw.githubusercontent.com`, but it does not explicitly warn that request parameters and metadata will be transmitted to third-party services. In this context, users may send wallet addresses, contract addresses, and query targets they assume are local or internal, creating a privacy and data-handling transparency gap.

Vague Triggers

Low
Confidence
81% confidence
Finding
This is a manifest/config file, so SQP-1 applies. The OpenAPI spec defines multiple generic operations and free-form string/path parameters such as "input", "chain", and "network" but provides no explicit invocation constraints, negative examples, or narrowing context that would help prevent overly broad matching if this spec is used to drive skill activation.

Static analysis

No suspicious patterns detected.