ClawHub
Back to skill

Security audit

eKYC Suite Media Labeling

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed KYC media-labeling client that sends selected media to a configured HTTPS backend, with no hidden persistence or unrelated data access found.

Install only for consented KYC/eKYC media-review workflows with a trusted eKYC backend, a valid API key, and an established retention policy. Expect submitted media, requested label codes, the API key, runtime headers, and any optional attribution environment variables you set to be sent to the configured HTTPS endpoint. Do not use the results as final identity or risk decisions without human review.

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 51, 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/media_labeling.py (reported line 69)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/media_labeling",
        json={
            "file": media_input(file_input),

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
# eKYC Suite Media Labeling Changelog

## 1.0.19 - 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
81% confidence
Finding

The documentation appears to be Chinese-only or mojibake-encoded without clear locale gating or user opt-in, which can cause operators or agents to misunderstand the skill's scope and usage constraints. In a regulated KYC context, unclear documentation increases the chance of incorrect invocation, mishandling of sensitive media, or missed safeguards.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description uses broad trigger terms such as generic image labeling, portrait labeling, and scene labeling, which can cause the agent to invoke this skill for requests outside narrowly scoped KYC onboarding review. In a security-sensitive identity workflow, overbroad routing can send unrelated user media to the eKYC backend, creating privacy, consent, and misprocessing risks.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/media_labeling.py (reported line 69)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/media_labeling",
        json={
            "file": media_input(file_input),

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/media_labeling.py:41