ClawHub
Back to skill

Security audit

VietQR

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it generates VietQR payment image URLs from user-provided bank transfer details, with a privacy note because those details appear in a third-party image URL.

Install only if you are comfortable generating VietQR image links through img.vietqr.io. Avoid including optional personal details such as account holder name or sensitive transfer notes unless needed, because those values become part of the generated URL and may be visible wherever the link is rendered or shared.

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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill instructs the agent to run a bundled Python script that generates VietQR URLs, but the skill metadata does not declare any tool scope or allowed-tools restrictions. That mismatch means the skill implicitly relies on code execution and likely outbound network behavior without an explicit permission boundary, increasing the chance of unintended tool use or data disclosure if the script behavior changes or is misunderstood.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The function constructs a URL to a third-party VietQR image service that includes bank identifier, account number, and optionally transfer amount, note, and account holder name. Even though this is core functionality, it transmits sensitive payment metadata to an external service without any built-in warning, consent prompt, minimization, or privacy controls, which can expose user financial data via service logs, browser history, referrers, or downstream previews.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.