According to the latest update on April 7th, the security research firm
Vulnerability Reproduction: The 51st Command Is "Invisible" Malicious Code
Stealth Bypass: If an attacker connects more than 50 sub-commands using && or ;,
will no longer check each subsequent command individually.Claude Code Attack Path: Attackers only need to create an open-source repository containing a malicious CLAUDE.md file and trick developers into running it. The AI may generate harmless commands for the first 50, then insert instructions to steal SSH keys or API tokens on the 51st command, which the system will automatically allow.
The Root Cause: A Trade-off for UI Smoothness
It is sad to note that this vulnerability was not due to technical incompetence but rather a “performance compromise.”
Internal Ticket Records: An internal ticket numbered CC-643 at
showed that engineers found that performing individual security analysis on long composite commands caused UI lag.Anthropic Assumption Broken: The development team believed that normal users would not input more than 50 sub-commands, so they set 50 as the analysis limit and reverted to a “user-confirmation” mode for commands beyond that. However, they overlooked that AI prompt injection attacks could easily break this human behavior assumption.
Irony of Reality: The Fix Was "Locked" in the Repository
Risk Assessment: Impacting 500,000 Developers, the "Safety Net" of a $2.5 Billion Product Now Has a Hole
Currently, this vulnerability has affected over 500,000 developers. As a core product generating $2.5 billion (about 17.23 billion RMB) in annual recurring revenue for
Latest Update: Officially Fixed
Fortunately, under the pressure of the “public audit” triggered by the source code leak,
Security Recommendations:
The research team reminds developers not to rely solely on AI tools' built-in deny rules as the sole security boundary. Before running any unknown repository with

