Noma Labs tricked GitHub's AI agent into leaking private repositories with a crafted issue. The prompt-injection flaw, GitLost, has no code fix.
A prompt injection attack can trick GitHub’s preview Agentic Workflows into retrieving content from private repositories and ...
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
A critical prompt injection vulnerability in GitHub Agentic Workflows could allow unauthenticated attackers to leak private repository data, ...
The flaw allows an unauthenticated attacker to craft a GitHub Issue in an org's public repository and then silently pull data ...
GitHub Inc.’s new Agentic Workflows feature that allowed an unauthenticated attacker to siphon data from private code ...
Mozilla 0DIN’s Claude Code demo shows how clean GitHub repos can expose AI coding agents to prompt injection, reverse shells, ...
Tom's Hardware on MSN
AI coding agents can be tricked into installing malware via 'clean' GitHub repositories
Three levels of indirection, all with seemingly innocuous steps, will catch a bot off-guard.
A security researcher, working with colleagues at Johns Hopkins University, opened a GitHub pull request, typed a malicious instruction into the PR title, and watched Anthropic’s Claude Code Security ...
Varonis Systems, Inc. (NASDAQ: VRNS), the data and AI security leader, today announced support for Cursor, the AI-native coding tool. Varonis Atlas provides runtime enforcement, threat detection, and ...
Anthropic is racing to contain the fallout after accidentally exposing the underlying instructions it uses to direct Claude Code, the popular artificial-intelligence agent app that has won the company ...
Results that may be inaccessible to you are currently showing.
Hide inaccessible results