ClawHub
Back to skill

Security audit

kmong

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Kmong registration helper, but it asks the agent to handle sensitive identity verification and CAPTCHA/SMS steps without adequate safeguards.

Review this carefully before installing. Use it only for your own authorized Kmong account, and do not let the agent view or store national-ID digits, SMS codes, CAPTCHA/security characters, or screenshots containing identity data. Prefer completing PASS verification and seller-term confirmation manually in the official browser interface.

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
Findings (1)

other

Warning
Location
SKILL.md:21
Finding

Automated CAPTCHA Handling and Sensitive Identity Verification Data Exposure

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly automates an identity-verification flow that requires entry of highly sensitive personal data, including name, birthdate, partial national ID/SSN information, phone number, SMS codes, and captcha handling, but provides no privacy, consent, storage, or exposure safeguards. This creates a real risk of credential and identity-data mishandling in an automation context, especially because screenshots and browser automation can capture or leak secrets across logs, images, or agent memory.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.