ClawHub
Back to skill

Security audit

CapSolver

Security checks across malware telemetry and agentic risk

Overview

This skill is transparent about using CapSolver, but it gives broad CAPTCHA and anti-bot bypass capability while sending sensitive challenge, proxy, and page data to a third party.

Install only if you intentionally need CapSolver automation and are authorized to solve challenges for the target sites. Treat API_KEY and proxy values as secrets, avoid sending private page HTML or account/session data, and review whether CAPTCHA or anti-bot bypass complies with the site rules and your policies.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill documentation indicates use of environment credentials and outbound network access to a third-party CAPTCHA-solving API, but no explicit permissions are declared. This creates a transparency and governance gap: agents or users may invoke a skill with external data exfiltration and secret usage capabilities they were not clearly warned about.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
This skill sends CAPTCHA materials, target site metadata, proxies, cookies, user-agent strings, and potentially page HTML or challenge artifacts to an external service, but the description does not warn users that sensitive browsing/session data may be transmitted off-platform. In this context, the omission is more dangerous because the skill is specifically designed to bypass anti-bot controls, so users may unknowingly expose authentication/session-related data and interact with third-party sites in ways that violate policy or terms.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
This skill is explicitly designed to submit captcha artifacts, target website details, and the API key to CapSolver's external API, but it provides no meaningful user-facing disclosure about what data leaves the local environment. In a security-sensitive agent context, that creates a real data exfiltration/privacy risk because page HTML, challenge material, proxies, and service credentials may be transmitted to a third party without informed consent or data minimization.

External Transmission

Medium
Category
Data Exfiltration
Content
raise TypeError(f"Unsupported type: {args.command}")

    def create_task(self) -> tuple[str, Any]:
        response = requests.post(
            f"{self.api_base}{self.create_task_endpoint}",
            headers=self.headers,
            json=self.create_task_payload,
Confidence
94% confidence
Finding
requests.post( f"{self.api_base}{self.create_task_endpoint}", headers=self.headers, json=

External Transmission

Medium
Category
Data Exfiltration
Content
def get_task_result(self, task_id: str) -> Optional[Dict[str, Any]]:
        self.get_task_result_payload['taskId'] = task_id
        response = requests.post(
            f"{self.api_base}{self.get_task_result_endpoint}",
            headers=self.headers,
            json=self.get_task_result_payload,
Confidence
83% confidence
Finding
requests.post( f"{self.api_base}{self.get_task_result_endpoint}", headers=self.headers, json=

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.32.4
python-dotenv>=0.9.9
Confidence
96% confidence
Finding
requests>=2.32.4

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.32.4
python-dotenv>=0.9.9
Confidence
95% confidence
Finding
python-dotenv>=0.9.9

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
93% confidence
Finding
requests

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.