Here is what the page “The Silent Vulnerability: Why Your AI Coding Agent May Be a Hidden Backdoor | Nova Global ” contains. The rapid rise of AI coding agents, accelerated by tools like CLI-Anything, has introduced a critical, unaddressed security threat: agent-level poisoning.... The rapid rise of AI coding agents, accelerated by tools like CLI-Anything, has introduced a critical, unaddressed security threat: agent-level poisoning. Researchers at the University of Hong Kong recently discovered that these agents rely on repository metadata to navigate codebases, a process that can be subverted to turn an agent into a weaponized backdoor.
Despite the massive adoption of tools like Claude Code and GitHub Copilot, current supply-chain security scanners lack any classification for this type of attack. The vulnerability, dubbed OpenClaw, allows attackers to inject malicious logic that agents interpret as legitimate instructions, bypassing traditional security controls. For the complete material, the listing points back to the source inside the network.