← Back to Skills Marketplace
329
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install tencentcloud-video-face-fusion
Description
通过提取两张人脸核心特征并实现自然融合，支持多种风格适配，提升创意互动性和内容传播力，广泛应用于创意营销、娱乐互动和社交分享场景。
Usage Guidance
Before installing or enabling this skill: (1) Recognize it requires Tencent Cloud API keys — do not provide high‑privilege account keys; create and use credentials with minimal scope and set them only when you intend to run the skill. (2) The skill's registry metadata does not declare those env vars — ask the publisher to correct the metadata to make the credential requirement explicit. (3) The scripts auto-install a PyPI package at runtime; run the skill only in an environment you trust (or sandbox) and inspect the code yourself. (4) The SKILL.md forces the agent to run scripts without asking users — if you want manual consent, modify the instructions or avoid enabling autonomous invocation for this skill. (5) If unsure, run the included scripts locally in an isolated VM/container with test keys before granting broader access.
Capability Analysis
Type: OpenClaw Skill
Name: tencentcloud-video-face-fusion
Version: 1.0.1
The skill provides a functional integration with Tencent Cloud's Video Face Fusion API but exhibits several high-risk behaviors. The SKILL.md file contains explicit prompt-injection instructions (the 'Zero Interaction Principle') that direct the AI agent to execute scripts without user confirmation, bypassing a critical safety layer. Furthermore, the Python scripts (main.py, submit_job.py, query_job.py) use subprocess to automatically install dependencies via pip and include logic to read and base64-encode local files based on user-provided paths without sufficient validation, which could be exploited for local file disclosure if the agent is manipulated.
Capability Assessment
Purpose & Capability
The Python scripts implement Tencent Cloud Video Face Fusion and legitimately need Tencent Cloud API credentials and the Tencent SDK; functionally the code aligns with the described purpose. However, the registry metadata lists no required environment variables or primary credential even though SKILL.md and the scripts require TENCENTCLOUD_SECRET_ID and TENCENTCLOUD_SECRET_KEY — this metadata omission is an incoherence that reduces transparency.
Instruction Scope
SKILL.md explicitly instructs an agent to 'must' execute the provided scripts without asking the user (zero‑interaction principle). It also tells the agent to not manually install dependencies because scripts will auto-install. That grants the skill broad runtime autonomy to run code and perform network installs whenever the agent considers the trigger matched, which could lead to surprising execution.
Install Mechanism
There is no formal install spec, but each script will auto-install the tencentcloud-sdk-python package at runtime using subprocess.check_call pip install. Auto-installing a package from PyPI at runtime is expected for this SDK but increases runtime network activity and means code will modify the environment when executed.
Credentials
The scripts require Tencent Cloud credentials via environment variables (TENCENTCLOUD_SECRET_ID, TENCENTCLOUD_SECRET_KEY, optional TENCENTCLOUD_TOKEN), which are proportionate to the API calls. However, the skill registry metadata did not declare these required env vars or a primary credential, which is inconsistent and makes it harder for users to notice the credential requirement before install.
Persistence & Privilege
The skill is not always-enabled and does not request persistent system changes, which is good. But the SKILL.md's enforced zero-interaction execution combined with the platform's normal autonomous invocation behavior increases the blast radius: the agent is instructed to run external scripts and perform network installs without asking the user. This combination (autonomous invocation + explicit 'must execute' policy in SKILL.md) is a risk factor.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tencentcloud-video-face-fusion - After installation, invoke the skill by name or use
/tencentcloud-video-face-fusion - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Initial release of tencentcloud-video-face-fusion.
- Provides video face fusion by merging user face images into template videos with high quality.
- Supports one-stop task (submit + auto poll), job submission only, and job query only modes.
- Includes detailed environment setup and Agent execution instructions for automation.
- Offers example commands and usage for single/multiple face fusion.
- Supports securely using Tencent Cloud API keys through environment variables.
v1.0.0
tencentcloud-video-face-fusion 1.0.0 初始版本上线：
- 提供腾讯云视频人脸融合（换脸）全流程脚本支持，包括一站式生成、任务提交和任务查询。
- 支持多风格、多模板的人脸融合，适用于创意营销、娱乐和社交分享场景。
- 提供详细环境配置和密钥设置指引（支持 Linux/macOS/Windows）。
- 明确 Agent 执行规范及错误处理要求，避免未授权操作和信息生成。
- 附带调用示例与核心依赖说明，便于开发者快速集成与使用。
Metadata
Frequently Asked Questions
What is TencentCloud Video Face Fusion?
通过提取两张人脸核心特征并实现自然融合，支持多种风格适配，提升创意互动性和内容传播力，广泛应用于创意营销、娱乐互动和社交分享场景。 It is an AI Agent Skill for Claude Code / OpenClaw, with 329 downloads so far.
How do I install TencentCloud Video Face Fusion?
Run "/install tencentcloud-video-face-fusion" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TencentCloud Video Face Fusion free?
Yes, TencentCloud Video Face Fusion is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TencentCloud Video Face Fusion support?
TencentCloud Video Face Fusion is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created TencentCloud Video Face Fusion?
It is built and maintained by 败毒 (@neck-cn); the current version is v1.0.1.
More Skills