agentic-qa

v0.1.0 suspicious
4.0
Medium Risk

Autonomous Agentic QA System for testing RAG pipelines and LLM systems.

🤖 AI Analysis

Final verdict: SUSPICIOUS

The package shows low risk in terms of network calls, shell execution, obfuscation, and credential harvesting. However, the metadata risk score is high due to the package's recent creation and the maintainer's lack of history on PyPI.

  • High metadata risk due to new maintainer
  • Recent package creation
Per-check LLM notes
  • Network: The detected network call patterns suggest the package is making HTTP requests, which could be normal if it's designed to communicate with an external service.
  • Shell: No shell execution patterns detected, indicating low risk for direct system command execution.
  • Obfuscation: No obfuscation patterns detected, indicating low risk.
  • Credentials: No credential harvesting patterns detected, indicating low risk.
  • Metadata: The package is suspicious due to its recent creation and the maintainer's lack of history with PyPI.

🔬 Heuristic Checks

Outbound Network Calls score 3.0

Found 2 network call pattern(s)

  • t} response = requests.post( self._endpoint, jso
  • t} response = requests.get( self._endpoint, par
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

No author email provided

Suspicious Page Links

All external links appear legitimate

Git Repository History score 3.0

Repository not found (deleted or private)

  • Repository not found (deleted or private)
Maintainer History score 6.0

3 maintainer concern(s) found

  • Only one version has ever been released — brand new package
  • Package uploaded less than 24 hours ago (2026-06-05T06:12:36.000Z)
  • Author "Your Name" appears to have only 1 package on PyPI (new or inactive account)