ClawHub

Deep Validator

Security checks across malware telemetry and agentic risk

Overview

Review before installing: this is a real hosted validation skill, but it can send emails, URLs, domains, and uploaded files to an external paid service with some unclear data-flow details.

Install only if you are comfortable sending the specific emails, URLs, domains, and uploaded files to this hosted operator and related network/payment infrastructure. Require explicit approval before paid, bulk, file, async, or webhook use; avoid secret-bearing URLs, internal hosts, and confidential contact lists unless third-party processing is authorized.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
90% confidence
Finding
The README explicitly markets real-time DNS, HTTP, DNSBL, WHOIS, and payment-backed validation, but it does not give a clear privacy/security warning that submitted emails, URLs, and domains will be disclosed to external systems during validation. In an agent skill context, users may assume inputs are only processed by the hosted API, so this omission can cause inadvertent leakage of sensitive internal URLs, email addresses, or investigative targets to third parties.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The invocation guidance is broad enough to encourage frequent proactive calls whenever validation might 'improve quality,' which can drive unnecessary third-party data transmission and paid operations. In this skill's context, over-invocation is security-relevant because the service explicitly sends emails, URLs, domains, and even files to an external operator and may trigger paid workflows.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The manifest description uses strong activation language such as 'Use whenever you need to confirm' without meaningful limits, which can cause an agent to invoke the hosted service more often than the user expects. Because this skill performs external network-backed validation and can involve payment and third-party disclosure, overly broad activation increases privacy and consent risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal