ClawHub
Back to skill

Security audit

tencentcloud-faceid-detectlivefaceaccurate

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Tencent Cloud face-liveness checker, but users should understand that face images or image URLs are sent to Tencent Cloud and require API credentials.

Install only if you intend to use Tencent Cloud for face liveness detection and have authorization or consent for any faces submitted. Store TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY securely, avoid exposing them in logs or screenshots, and do not submit biometric images unless third-party cloud processing is acceptable.

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)

Vague Triggers

Medium
Confidence
81% confidence
Finding
The trigger conditions are broad enough to activate the skill for many generic face-image or liveness-related requests, which can cause over-invocation of a third-party biometric processing API. In this context, overbroad triggering is risky because the skill handles highly sensitive facial images and may send them to Tencent Cloud when a narrower or more privacy-preserving action would suffice.

Missing User Warnings

High
Confidence
96% confidence
Finding
The skill description does not clearly disclose that submitted face images or image URLs will be transmitted to Tencent Cloud for biometric analysis. Because facial images are highly sensitive personal data, lack of upfront notice and consent materially increases privacy, compliance, and trust risks, especially if the skill is auto-triggered.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation lists sensitive credential environment variables but provides no security guidance on storing, rotating, or preventing exposure of those secrets. This increases the chance of accidental leakage through shell history, logs, screenshots, or unsafe deployment practices, which could enable unauthorized API use.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal