← Back to Skills Marketplace
TencentCloud FaceID DetectAIFakeFaces
by
hzzhanglijie
· GitHub ↗
· v1.0.3
· MIT-0
375
Downloads
0
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install tencentcloud-faceid-detectaifakefaces
Description
腾讯云AI人脸防护盾(DetectAIFakeFaces)接口调用技能。当用户需要对人脸图片或视频进行防攻击检测时,应使用此技能。可针对性有效识别高仿真的AIGC换脸、高清翻拍、批量黑产攻击、水印等攻击痕迹,增强对图片和视频的防伪安全能力。支持图片Base64和视频Base64两种输入方式。
Usage Guidance
Before installing or enabling this skill: (1) Be aware the script will send images/videos (biometric data) to Tencent Cloud — ensure you have legal consent and you are comfortable sharing that data with Tencent. (2) The skill requires TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY, but the registry metadata omits this — verify and supply least-privilege Tencent credentials (preferably an account/role restricted to the FaceID API). (3) Verify the publisher/source and prefer packages with a homepage or repository; provenance is missing here. (4) Review the included scripts yourself or run in an isolated environment; verify you trust the pip package tencentcloud-sdk-python (check versions and checksums). (5) Consider network and logging controls so image data and API keys cannot be exfiltrated beyond the intended Tencent endpoint. If you need higher assurance about provenance or metadata accuracy, request the publisher to update the registry metadata to declare the required env vars and provide a homepage or source repository.
Capability Analysis
Type: OpenClaw Skill
Name: tencentcloud-faceid-detectaifakefaces
Version: 1.0.3
The skill is a legitimate wrapper for the Tencent Cloud DetectAIFakeFaces API, designed to detect AI-generated or tampered faces in images and videos. The implementation in `scripts/main.py` follows standard practices for cloud SDK integration, including proper environment variable handling for credentials and size-limited file processing. No indicators of malicious intent, data exfiltration, or prompt injection were identified.
Capability Assessment
Purpose & Capability
The SKILL.md and scripts/main.py clearly implement calls to Tencent Cloud's DetectAIFakeFaces API and require Tencent Cloud API keys. However the registry metadata reported earlier lists no required environment variables or primary credential. That omission is an incoherence: the skill will fail without TENCENTCLOUD_SECRET_ID/TENCENTCLOUD_SECRET_KEY, so the metadata is inaccurate and reduces trust/provenance.
Instruction Scope
The runtime instructions and scripts are narrowly scoped: they read a provided file or Base64 input, enforce size/type limits, Base64-encode local files if needed, and call faceid.tencentcloudapi.com via the official SDK. The instructions do not attempt to read arbitrary system files or unrelated environment variables. They do require the Tencent Cloud credentials and a pip dependency as documented in SKILL.md.
Install Mechanism
This is instruction-only with an included Python script and no install spec. Dependencies are obtained via pip (tencentcloud-sdk-python), which is normal for a Python client. There are no downloads from untrusted URLs or archive extraction steps in the package itself.
Credentials
The script requires TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY — these are proportionate and expected for calling the Tencent Cloud API. The concern is that the registry metadata did not declare these required environment variables or a primary credential, creating an inconsistency that affects expectations about what secrets will be needed.
Persistence & Privilege
The skill does not request permanent presence (always=false) and does not modify other skills or system-wide settings. It does not persist credentials or reconfigure the agent. Autonomous invocation is allowed by default but is not combined here with broad undeclared access.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tencentcloud-faceid-detectaifakefaces - After installation, invoke the skill by name or use
/tencentcloud-faceid-detectaifakefaces - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- 增加了隐私与合规性说明，提醒用户需合法取得人脸等个人信息的授权或合法性基础
- 其他功能和使用方式保持不变
v1.0.2
- 风险等级说明中的“Normal”已更名为“Mid”以统一表述方式。
- 其余内容保持不变。
v1.0.1
Version 1.0.1
- No file changes detected.
- No updates or modifications from the previous version.
- Behavior, usage, and documentation remain the same as before.
v1.0.0
Initial release of Tencent Cloud AI Face Shield (DetectAIFakeFaces) skill:
- Provides detection of AI-generated faces, deepfakes, screen recapture, watermark, and synthetic attacks in images or videos.
- Supports both image (jpg/png) and video (mp4/avi/flv) inputs in Base64 or file path format.
- Returns detailed JSON results on risk level and specific detected attack types.
- Includes environment setup instructions and usage examples for Python 3.6+.
- Offers clear input requirements and descriptions for attack risk and types.
Metadata
Frequently Asked Questions
What is TencentCloud FaceID DetectAIFakeFaces?
腾讯云AI人脸防护盾(DetectAIFakeFaces)接口调用技能。当用户需要对人脸图片或视频进行防攻击检测时,应使用此技能。可针对性有效识别高仿真的AIGC换脸、高清翻拍、批量黑产攻击、水印等攻击痕迹,增强对图片和视频的防伪安全能力。支持图片Base64和视频Base64两种输入方式。 It is an AI Agent Skill for Claude Code / OpenClaw, with 375 downloads so far.
How do I install TencentCloud FaceID DetectAIFakeFaces?
Run "/install tencentcloud-faceid-detectaifakefaces" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TencentCloud FaceID DetectAIFakeFaces free?
Yes, TencentCloud FaceID DetectAIFakeFaces is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TencentCloud FaceID DetectAIFakeFaces support?
TencentCloud FaceID DetectAIFakeFaces is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TencentCloud FaceID DetectAIFakeFaces?
It is built and maintained by hzzhanglijie (@hzzhanglijie); the current version is v1.0.3.
More Skills