ClawHub
Back to skill

Security audit

AnySearch MCP

Security checks across malware telemetry and agentic risk

Overview

This is a coherent remote search connector, but users should understand that AnySearch receives searches, extracted URLs/page content, and optional registration email/API-key data.

Install this only if you are comfortable using AnySearch as a remote search provider. Treat API keys as secrets, confirm before account creation, and do not use URL extraction on private or confidential pages unless you intend to disclose that URL and its fetched content to AnySearch.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the agent to collect a real user email, transmit it to a third-party registration endpoint, and handle a one-time plaintext API key/password onboarding flow without a clear consent and privacy warning. This creates privacy and account-security risk because users may not understand that their personal data is being sent off-platform and that credentials are being provisioned through an email-based flow with no stronger identity verification.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill advertises full-page URL extraction but does not warn that submitted URLs and fetched page contents are processed by a remote AnySearch service. Users may provide sensitive internal, pre-release, or private URLs assuming local handling, resulting in unintended disclosure of browsing targets and page contents to a third party.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
| starts with `Key creation failed.` | account created but key failed — extract the email and URL from the message (`"Key creation failed. Your account <email> was created; sign in at <url>."`) and tell the user to sign in there to create a key manually |
| `Internal server error.`          | retry later or fall back to anonymous                                                               |

> The email **must be real and reachable** — the password is delivered there. There is **no verification code** in this flow; the agent only ever asks for an email.

### Get an API Key
Confidence
88% confidence
Finding
no verification

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.