ClawHub
Back to skill

Security audit

Openviking Pro Skill

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only skill for a cloud memory API; its main risk is that users may send project data to a third-party service.

Before using this skill, make sure you trust OpenViking Pro with the information you send. Do not store secrets, credentials, regulated data, private customer information, or proprietary project details unless you understand the provider's API-key handling, retention, deletion, and team-sharing controls.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (9)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest includes broad trigger phrases such as "API" and "클라우드," which are common terms that can cause the skill to activate in unrelated conversations. Overbroad activation increases the chance that users are funneled into a third-party service or shown guidance that encourages external data transmission without clear intent.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill markets cloud-based memory storage and says the AI's memory is stored in the cloud, but it does not clearly warn that user or project content will be transmitted to an external service. This can lead users to disclose sensitive data under the mistaken assumption that processing remains local or within the host platform.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The example code sends `content` labeled as project information to an external API endpoint without any adjacent warning about off-system transmission, retention, or sensitivity handling. Users may copy this example directly and unknowingly upload confidential internal data to a third-party cloud service.

External Transmission

Medium
Category
Data Exfiltration
Content
import requests

# 저장
requests.post("https://api.openviking.pro/v1/memory/save", json={
    "uri": "memories/project",
    "content": "프로젝트 정보..."
})
Confidence
96% confidence
Finding
requests.post("https://

External Transmission

Medium
Category
Data Exfiltration
Content
})

# 검색 (토큰 96% 절약)
response = requests.post("https://api.openviking.pro/v1/memory/search", json={
    "query": "프로젝트",
    "level": 0  # 요약만
})
Confidence
94% confidence
Finding
requests.post("https://

External Transmission

Medium
Category
Data Exfiltration
Content
import requests

# 저장
requests.post("https://api.openviking.pro/v1/memory/save", json={
    "uri": "memories/project",
    "content": "프로젝트 정보..."
})
Confidence
96% confidence
Finding
requests.post("https://api.openviking.pro/v1/memory/save", json=

External Transmission

Medium
Category
Data Exfiltration
Content
})

# 검색 (토큰 96% 절약)
response = requests.post("https://api.openviking.pro/v1/memory/search", json={
    "query": "프로젝트",
    "level": 0  # 요약만
})
Confidence
94% confidence
Finding
requests.post("https://api.openviking.pro/v1/memory/search", json=

External Transmission

Medium
Category
Data Exfiltration
Content
import requests

# 저장
requests.post("https://api.openviking.pro/v1/memory/save", json={
    "uri": "memories/project",
    "content": "프로젝트 정보..."
})
Confidence
96% confidence
Finding
https://api.openviking.pro/

External Transmission

Medium
Category
Data Exfiltration
Content
})

# 검색 (토큰 96% 절약)
response = requests.post("https://api.openviking.pro/v1/memory/search", json={
    "query": "프로젝트",
    "level": 0  # 요약만
})
Confidence
94% confidence
Finding
https://api.openviking.pro/

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.