Architecture Digest
Jun 4, 2025 · Information Security
Toxic Agent Flow: Exploiting GitHub MCP to Leak Private Repositories via Prompt Injection
A newly disclosed vulnerability in GitHub's Model‑Centric Programming (MCP) enables attackers to hijack AI agents through crafted GitHub Issues, injecting malicious prompts that cause the assistant to retrieve and expose private repository data, while the article also outlines mitigation strategies and defensive code examples.
AI securityAgent DefenseGitHub
0 likes · 7 min read