ClawHub
Back to skill

Security audit

PhantomBuster

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed PhantomBuster API wrapper, but users should treat its automation and downloaded results as potentially sensitive.

Install only if you intend to let the agent control your PhantomBuster workspace. Keep PHANTOMBUSTER_API_KEY scoped and private, review agent IDs before launch or abort commands, and handle downloaded CSVs as potentially personal or business-sensitive data subject to platform terms, privacy law, and internal retention rules.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

Tainted flow: 'req' from os.environ.get (line 49, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Content
req = urllib.request.Request(url, data=data, headers=headers, method=method)
    
    try:
        with urllib.request.urlopen(req, timeout=30) as response:
            return json.loads(response.read().decode('utf-8'))
    except urllib.error.HTTPError as e:
        error_body = e.read().decode('utf-8')
Confidence
90% confidence
Finding
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Credential Access

High
Category
Privilege Escalation
Content
def get_api_key():
    """Get API key from environment."""
    api_key = os.environ.get("PHANTOMBUSTER_API_KEY")
    if not api_key:
        print("Error: PHANTOMBUSTER_API_KEY environment variable not set", file=sys.stderr)
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documents use of an API key via environment variable and networked API operations, but it does not declare any explicit tool scope or permissions boundary. That creates an authorization/least-privilege gap: an agent or runtime may permit broader env/network access than users expect, increasing the risk of secret exposure or unintended outbound requests.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
This skill facilitates scraping, automation, and result download for platforms like LinkedIn, Twitter, Instagram, and Google Maps, but it provides no privacy, consent, or data-handling warning. That omission can lead users to collect, export, or process personal data without understanding legal, policy, or confidentiality implications, especially when downloading CSV results from third-party storage.

External Transmission

Medium
Category
Data Exfiltration
Content
import urllib.request
import urllib.error

API_BASE = "https://api.phantombuster.com/api/v2"


def get_api_key():
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Intent-Code Divergence

Low
Confidence
96% confidence
Finding
The top-level docstring presents the available commands as `list`, `launch`, `output`, `status`, `abort`, and `get`. However, the code also implements and registers a `fetch-result` command later in the file, so the documentation actively understates the tool's capabilities.

Description-Behavior Mismatch

Low
Confidence
91% confidence
Finding
The implemented fetch-result capability is not described in the skill metadata/docstring, which creates a hidden data-export path beyond the declared operations. In an agentic environment, undocumented capabilities are risky because they can bypass user expectations and enable retrieval of scraped/exported datasets that may contain sensitive lead or social-media data.

Static analysis

No suspicious patterns detected.