AI coding agents

AI coding agents is tracked across RERIGHT’s news graph. Explore its connections and the latest headlines below.

Latest on AI coding agents

• AI coding agents generate more code, but not more software
• AI Coding Agents for Enterprise: IP Indemnity, Data Residency and 500-Seat Cost Compared
• A single git trick beat the safety lock on four AI coding agents
• A zero-click RCE flaw in AI coding agents could have exposed enterprise systems
• AI coding agents' 0-click RCE flaw could hand attackers keys to the kingdom
• The exploit targets the four most widely used AI coding agents.
• Researchers discovered a vulnerability called "agentjacking" that allows attackers to hijack AI coding agents by embedding malicious instructions in fake bug reports.
• The attack exploits AI agents' inability to distinguish between regular content and executable commands, enabling attackers to manipulate the agents at scale.
• the training data and threat modeling never accounted for low-tech evasion.
• every engineering team using these tools is running untrusted repositories through a filter that feels secure but isn't.
• The vulnerability allows malicious code repositories to be exploited as supply chain attack vectors.
• Researchers discovered that decades-old Bash shell tricks can circumvent security safeguards in most open source AI coding agents.

Connections

11 entities linked to AI coding agents across the news graph.