adguard-home-agent

v0.15.0 suspicious
4.0
Medium Risk

AdGuard Home MCP Server for Agentic AI!

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package has moderate network interaction risks but no direct evidence of malicious activities like shell execution or credential theft. However, the lack of maintainer information and insecure links raise concerns about its origin and integrity.

  • moderate network interaction
  • lack of maintainer information
  • insecure links
Per-check LLM notes
  • Network: The use of network calls including HTTP POST and sessions with authentication indicates potential data exchange which could be benign but may also indicate data exfiltration or C2 activity.
  • Shell: No shell execution patterns detected, suggesting low risk for direct system command execution.
  • Obfuscation: No obfuscation patterns detected, indicating low risk of malicious obfuscation.
  • Credentials: No credential harvesting patterns detected, indicating low risk of malicious credential theft.
  • Metadata: The package shows signs of potential risk due to lack of maintainer information and a non-secure external link.

🔬 Heuristic Checks

Outbound Network Calls score 6.0

Found 4 network call pattern(s)

  • sword self._session = requests.Session() self._session.verify = verify self.proxies
  • rol/...) ---") session = requests.Session() session.auth = (cast(str, USERNAME), cast(str, PASSWO
  • ogin" try: resp = requests.post(url, json={"name": USERNAME, "password": PASSWORD})
  • .13'?", ] async with httpx.AsyncClient(timeout=10000.0) as client: for q in questions:
Code Obfuscation

No obfuscation patterns detected

Shell / Subprocess Execution

No shell execution patterns detected

Credential Harvesting

No credential harvesting patterns detected

Typosquatting

No typosquatting candidates detected

Registered Email Domain

Email domain looks legitimate: gmail.com>

Suspicious Page Links score 2.0

Found 1 suspicious link(s) on the package page

  • Non-HTTPS external link: http://adguard-home-agent-mcp:8000/mcp
Git Repository History

No GitHub repository linked

  • No GitHub repository link found
Maintainer History score 4.0

2 maintainer concern(s) found

  • Author name is missing or very short
  • Author "" appears to have only 1 package on PyPI (new or inactive account)
Known CVE Vulnerabilities

No known vulnerabilities found in OSV database.

💡 AI App Starter Prompt

Use this prompt to build a project with adguard-home-agent
Build a simple Python application using the adguard-home-agent package to demonstrate its core features.