ClawHub
Back to skill

Security audit

Global Market Feed

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed QuoteNode market-data REST helper that sends user-provided requests and an API key to allowlisted datatk HTTPS endpoints.

Install only if you intend to use QuoteNode/dataTrack market-data APIs. Keep env.json private, use a trusted datatk endpoint, and avoid placing unrelated sensitive data in request bodies because the script sends the body and API key to the configured service.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Ae1

High
Category
analysis-evasion
Content
- `scripts/request.mjs`: generic POST caller for any REST endpoint.
Confidence
100% confidence
Finding
Referenced artifact was not completely inspected

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill explicitly instructs users to invoke a network-enabled script and send requests to external endpoints, but the manifest declares no tool scope such as `permissions` or `allowed-tools`. This creates a mismatch between declared and actual capabilities, reducing transparency and policy enforcement and increasing the risk of unintended or unauthorized outbound network access with user-supplied credentials.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
This code performs a network request that sends user-supplied JSON and an API key to a remote endpoint, which is a safety-relevant operation under the code-file warning criteria. While the script validates the endpoint and prints errors on failure, it does not provide a user-facing disclosure or confirmation before transmitting the data, and there is no nearby comment or docstring explaining that this action sends data externally.

Static analysis

No suspicious patterns detected.