Return to Threats

New ChocoPoC RAT Targets Vulnerability Researchers via Fake PoC Exploit Repos

thehackernews.com 2026-07-02 malicious AI use High

What Happened

Attackers are hiding a data-stealing trojan inside fake exploit code aimed at the people who hunt bugs for a living. The malware, called ChocoPoC, travels in Python proof-of-concept (PoC) repositories on GitHub that claim to exploit hot new CVEs. Run one, and it quietly lifts your saved passwords, browser cookies, and files, then hands the attacker a shell on your machine. YesWeHack and

Why It Matters

The article reports that attackers are distributing a Python-based remote access trojan called ChocoPoC through fake GitHub PoC exploit repositories claiming to target recent CVEs, specifically aimed at vulnerability and security researchers.[1][2][3] Once executed, the malware steals browser passwords, cookies, autofill data, shell history, text and database files, and allows arbitrary command and Python code execution, using Mapbox datasets and a separate HTTP server for data exfiltration.[1][2][3] From a CyberSE.AI perspective, this illustrates malicious use of code repositories and tooling that security teams (and AI-assisted research workflows) rely on, underscoring the need to treat third-party PoCs and dependencies as part of the AI/software supply chain and to run untrusted code only in isolated, hardened environments. Organizations should implement continuous red teaming of their research and automation environments, adopt SBOM-driven controls for dependencies, and establish CISO-level policies that govern the safe use of public PoCs and code in any security or AI-assisted analysis pipeline.

Healthcare Fintech SaaS SMB AI startups

CyberSE Analysis

This signal maps to malicious AI use. Organizations using AI agents, LLM APIs, SaaS integrations, or sensitive data workflows should review whether this class of issue could create unauthorized tool execution, data leakage, weak approval gates, or unmanaged supply-chain exposure.

Recommended Actions

  • Restrict AI agent tool permissions and production write paths.
  • Review sensitive data access across prompts, logs, embeddings, memory, and SaaS integrations.
  • Add human approval workflows for high-impact or state-changing actions.
  • Run prompt injection and indirect prompt injection tests against affected workflows.
  • Document the owner, control gap, and remediation deadline for this risk class.

Source

https://thehackernews.com/2026/07/new-chocopoc-rat-targets-vulnerability.html

Talk to AI CISO