iFLYTEK Face Compare

Compare two face images and return similarity score using iFlytek Face Recognition API.

Security Scan

The skill's code, declared environment variables, and runtime instructions are coherent with its stated purpose (calling iFlytek's face-compare API); nothing in the files suggests hidden exfiltration or unrelated access.

Purpose & Capability

Name/description ask to compare two face images via iFlytek. The skill requires iFlytek credentials (app id/key/secret), reads two image files, encodes them, and POSTs to an xfyun API endpoint — all consistent with the described purpose.

Instruction Scope

SKILL.md and the Python script both limit actions to validating and reading two image files, encoding them, signing a request, and sending it to the iFlytek API. There are no instructions to read other files, collect unrelated environment variables, or transmit data to unexpected endpoints.

Install Mechanism

There is no install spec (instruction-only), which minimizes write-to-disk risk, but the bundled script imports the third-party 'requests' module while SKILL.md only declares 'python3' as a required binary and doesn't mention dependencies. This is a usability/packaging omission (runtime failure if 'requests' isn't present) rather than a security indicator, but you should ensure the runtime has required Python packages.

Credentials

The three required environment variables (XF_FACE_APP_ID, XF_FACE_API_KEY, XF_FACE_API_SECRET) directly correspond to authenticating with the iFlytek API. No unrelated credentials or broad system secrets are requested.

Persistence & Privilege

The skill does not request always:true and does not modify other skills or system settings. It only reads environment variables at runtime and does not persist additional configuration or tokens itself.

Assessment

This skill appears to do what it claims, but before installing: (1) Confirm you trust the iFlytek endpoint (https://api.xf-yun.com) and understand privacy/legal implications of uploading facial images to a third-party service. (2) Ensure you provide only valid iFlytek credentials and store them securely — the SKILL.md suggests putting them in ~/.openclaw/openclaw.json which will store secrets on disk. (3) Ensure the runtime environment has the required Python libraries (requests) or install them in a controlled manner. (4) Review your organization's policy on biometric data handling and retention before using this in production. If you need higher assurance, inspect the final lines of the included script (it was truncated in the package listing) to verify there are no additional hidden behaviors.

👤 Face Compare

Compare two face images and calculate their similarity score using iFlytek's advanced face recognition technology.

Designed for identity verification, face matching, and security authentication scenarios.

---

✨ Features

• High-accuracy face comparison
• Base64 image encoding support
• Multiple image format support (jpg, png, bmp)
• Detailed similarity scoring
• One-command execution

---

🚀 Usage

python {baseDir}/scripts/index.py "<image1_path>" "<image2_path>"

Example:

python {baseDir}/scripts/index.py "/path/to/face1.jpg" "/path/to/face2.jpg"

📋 Input Specification

Image Requirements

• Supported formats: JPG, PNG, BMP
• File size: < 4MB recommended
• Image should contain clear, frontal face
• One face per image for best results

---

⚠ Constraints

• Both image paths must be valid and accessible
• Images must contain detectable faces
• API credentials must be configured
• Network connection required

---

🔧 Environment Setup

Required:

• Python available in PATH
• Environment variables configured:

export XF_FACE_APP_ID=your_app_id
export XF_FACE_API_KEY=your_api_key
export XF_FACE_API_SECRET=your_api_secret

Or configure it in ~/.openclaw/openclaw.json:

{
	"env": {
		"XF_FACE_APP_ID": "your_app_id",
		"XF_FACE_API_KEY": "your_api_key",
		"XF_FACE_API_SECRET": "your_api_secret"
	}
}

---

📦 Output

Returns JSON response with:

• Similarity score (0-100)
• Comparison result (same person or not)
• Confidence level
• Face detection status

---

🎯 Target Use Cases

• Identity verification
• Access control systems
• Duplicate account detection
• Photo matching services
• Security authentication
• Attendance systems

---

🛠 Extensibility

Future enhancements may include:

• Batch face comparison
• Face quality assessment
• Multiple face detection
• Liveness detection integration
• Custom threshold configuration

---

Built for automation workflows and AI-driven identity verification.