ClawHub
Back to skill

Security audit

eKYC Suite Face Compare

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed eKYC face-comparison client that uploads two user-supplied face images to a configured HTTPS backend, with no evidence of hidden execution, persistence, or unrelated data access.

Install only if you have authority to process the face images, an appropriate retention/deletion policy with the configured eKYC backend, and a human-reviewed KYC workflow. Do not use it for liveness, OCR, broad face recognition, or fully automated identity decisions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (6)

Tainted flow: 'headers' from os.environ.get (line 48, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/face_compare.py (reported line 66)May include surrounding context.

python
"x-ekyc-install-id": os.environ.get("EKYC_INSTALL_ID"),
    }
    headers.update({key: value for key, value in optional.items() if value})
    response = requests.post(
        f"{endpoint}/api/v1/tools/face_compare",
        json={
            "photo1": media_input(photo1),

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · CHANGELOG.md (reported line 1)May include surrounding context.

md
# Changelog

## 1.0.17 - 2026-08-17

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file is a Chinese-language skill document and does not indicate that language selection is optional or that the skill is intentionally restricted to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The default prompt uses broad trigger phrases like 'selfie verification', 'face matching', and 'KYC onboarding face match' without embedding strong limiting conditions such as consent checks, human-review requirements, or explicit exclusions for high-impact automated decisions. This can cause an agent/router to invoke the skill for loosely related or overly broad identity-verification requests, increasing the chance of inappropriate biometric processing or use outside the intended scope.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
98% confidence
Finding

This skill uploads two face images, and potentially local file contents converted to base64, to an external cloud service. Because the data is biometric and highly sensitive KYC material, external transmission materially increases privacy, compliance, and breach impact even though it is the intended function of the skill.

Content

Scanner excerpt · scripts/face_compare.py (reported line 66)May include surrounding context.

python
"x-ekyc-install-id": os.environ.get("EKYC_INSTALL_ID"),
    }
    headers.update({key: value for key, value in optional.items() if value})
    response = requests.post(
        f"{endpoint}/api/v1/tools/face_compare",
        json={
            "photo1": media_input(photo1),

Static analysis

Detected: suspicious.potential_exfiltration

Python code base64-encodes a local file and sends it over the network.

Critical
Code
suspicious.potential_exfiltration
Location
scripts/face_compare.py:40