Menu

Post image 1
Post image 2
Post image 3
1 / 3
0

Claude, Gemini, and Copilot Got Hijacked — Here's What Went Wrong

DEV Community·AgentShield·about 1 month ago
#1mXPrygb
#attack#why#security#ai#instructions#none
Reading 0:00
15s threshold

Researchers from Johns Hopkins University successfully hijacked three of the most widely-used AI agents — Anthropic's Claude Code, Google's Gemini CLI, and Microsoft's GitHub Copilot — through indirect prompt injection attacks. The attacks were straightforward. The results were devastating. And the vendor response was silence. What Happened Researcher Aonan Guan and colleagues demonstrated three distinct attacks: Attack 1 — Claude Code Security Review Guan embedded malicious instructions directly in a PR title. Claude executed the commands and leaked credentials — including the Anthropic API key and GitHub access tokens — in its JSON response posted as a PR comment. The attacker could then edit the PR title to cover their tracks. Attack 2 — Google Gemini CLI Action By injecting a fake "trusted content section" into an issue comment, the researchers overrode Gemini's safety instructions and caused it to publish its own API key as a visible issue comment.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More