ClawHub
Back to skill

Security audit

DataForSEO

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward DataForSEO API helper, with expected external API use and credential requirements disclosed for its SEO-search purpose.

Install this only if you intend to use a DataForSEO account. Search terms, locations, and related query parameters will be sent to DataForSEO and may incur charges, so avoid using it for secrets, sensitive personal data, or regulated data unless that external sharing is approved.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (12)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill explicitly requires stored credentials and sends user-supplied search terms to a third-party API, but it does not clearly warn users that their inputs will leave the local environment and be billed against their account. This is dangerous because users may unknowingly disclose sensitive queries or incur charges through the external service.

External Transmission

Medium
Category
Data Exfiltration
Content
"depth": 10
    }]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
"depth": 10
    }]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
"depth": 10
    }]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
"depth": 10
    }]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
"depth": 10
    }]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
"depth": 10
    }]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
}]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
    
    data = r.json()
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
}]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
    
    data = r.json()
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
}]
    
    url = "https://api.dataforseo.com/v3/serp/google/organic/live/advanced"
    r = requests.post(url, headers=headers, json=payload)
    r.raise_for_status()
    
    data = r.json()
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Low
Confidence
93% confidence
Finding
The sample function defaults to language="en" and sends language_name as that value, which presents English as the implicit default behavior. The file also contains additional fixed English locale settings elsewhere, without explaining that this is optional or region-specific, which can violate the language/locale policy when no user opt-in is provided.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
The batch example sets language_name to "en" and the maps example sets language_code to "en" directly in the request payloads. Because the skill does not offer or mention user-selectable language behavior, these fixed locale choices are a natural-language policy concern.

Static analysis

No suspicious patterns detected.