ClawHub
Back to skill

Security audit

TencentCloud FaceID CompareFace

Security checks across malware telemetry and agentic risk

Overview

This skill performs Tencent Cloud face comparison, but it handles biometric images with broad triggering and weak user-facing consent/privacy disclosure.

Review before installing. Use this only for images you have permission to compare, with least-privileged Tencent Cloud credentials, and assume submitted images or image URLs leave your local environment for Tencent Cloud processing. Avoid ambiguous requests and remote URLs unless you intentionally want this provider to process that biometric data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill documentation states that Tencent Cloud credentials must be supplied through environment variables, but the skill does not declare permissions or explicitly disclose this capability. Hidden or undeclared access to secrets increases the risk of over-privileged execution and makes it harder for users or platforms to assess what sensitive resources the skill can access.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger guidance includes a catch-all phrase for essentially any face-comparison-related scenario, which is broad enough to cause invocation in unintended contexts. Overbroad routing can expose biometric data to a third-party cloud API when the user did not specifically intend to use this provider or this exact operation.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
This skill processes highly sensitive biometric data and also supports remote image URLs, but the documentation does not warn users about privacy, consent, retention, third-party processing, or risks from fetching remote content. In this context, missing risk disclosure is significant because face data is sensitive and transmitting it to an external service can create compliance, privacy, and user-consent issues.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The script transmits highly sensitive biometric data (face images or remote image URLs) to Tencent Cloud, but there is no explicit user-facing consent, privacy notice, or warning at the point of transmission. In a skill context, users may not realize their images are leaving the local environment and being processed by a third-party cloud provider, creating privacy, compliance, and trust risks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.