ClawHub
Back to skill

Security audit

QRCode Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill does generate QR codes, but it automatically sends whatever text you encode to a third-party QR service and documents that risk inconsistently.

Review this before installing if you might encode passwords, tokens, internal URLs, contact details, or Wi-Fi credentials. Treat all QR payloads as shared with api.qrserver.com, and avoid the JSON output for sensitive content because it includes the generated request URL.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/qrcode_generator.py:27
Finding

Arbitrary QR Payloads Are Disclosed to a Third-Party Service and Re-Exposed in JSON Output

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill description understates behavior by presenting itself as a simple QR generator while transmitting user-provided text/URLs to an external service and apparently supporting behaviors not fully declared in the metadata. This is dangerous because users may enter secrets, Wi-Fi credentials, contact data, or internal URLs believing processing is local, causing unintended third-party disclosure.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill performs network access to a third-party QR code API but does not declare any tool scope, permissions, or allowed-tools metadata. This creates an authorization and transparency gap: hosts or users may assume the skill is local-only while user-supplied content is actually transmitted externally.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The implementation relies on a third-party web API to generate QR codes, despite the skill description implying a simple local capability and emphasizing that no API key is required. This creates an undisclosed dependency on an external service, which introduces privacy, availability, and supply-chain risk because user input is sent off-system and functionality breaks if the service is unavailable or changes behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script does not clearly notify users that the provided text or URL will be transmitted to an external service for QR code generation. This lack of transparency is dangerous because users may reasonably assume QR generation is local and unknowingly disclose confidential or regulated data.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

User-supplied text and URLs are embedded into a request to api.qrserver.com, meaning potentially sensitive content is transmitted to an external party. In this skill context, users may encode secrets, Wi-Fi credentials, tokens, or internal URLs into QR codes, so the off-system transmission materially increases confidentiality risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The code makes an outbound HTTPS request to a third-party endpoint and includes user-controlled content in that request. While external communication is not inherently malicious, in this skill it is security-relevant because it exposes all encoded data to an external service and creates dependency on that service's trustworthiness and availability.

Content

Scanner excerpt · scripts/qrcode_generator.py (reported line 30)May include surrounding context.

python
dict with success status and data/base64 or error message
    """
    encoded_text = urllib.parse.quote(text)
    url = f"https://api.qrserver.com/v1/create-qr-code/?size={size}x{size}&margin={margin}&format={format}&data={encoded_text}"
    
    headers = {
        'User-Agent': 'QRCode-Tool/1.0 (https://github.com/qiance)'

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest sets language: en, which indicates an English-only locale choice in the skill metadata. Although the file also contains a Chinese section later, there is no explicit user opt-in or explanation that the locale restriction is intentional or region-specific, so this is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.