Tag

indirect prompt injection

4 articles

Latest in indirect prompt injection

A Simple Website Summary Just Exposed the Limits of AI Coding Guardrails

Claude Code’s Auto Mode was bypassed in an attack chain that turned a routine webpage summary into remote code execution, highlighting the limits of AI agent guardrails.

Aug 31, 20263 min

All indirect prompt injection Articles

Showing 1–4 of 4

Jul13

‘HalluSquatting’ Compromises AI Coding Agents to Install Malware, Create Botnets

Hallucinations have been an ongoing problem since OpenAI first introduced its ChatGPT chatbot in November 2022, highlighting generative AI’s tendency to generate plausible but fals…

3 min

Jul08

‘GitLost’ Flaw Lets Attackers Trick GitHub AI Agent Into Leaking Private Repos

Noma researchers again show how easy it is to manipulate AI agents with malicious commands via indirect prompt injection attacks.

3 min

Jun30

Mozilla Shows the Danger of Indirect Prompt Injections in AI Coding Agents

A clean GitHub repository that contains no malicious code can launch an attack and fully compromise a developer’s systems by using indirect prompt injections to trick AI-powered co…

3 min