ainewsblitz.com

Breaking

Researchers Unveil 'Ghostcommit' Attack That Hides Malicious Prompts in Images to Hijack AI Coding Agents

Researchers Unveil 'Ghostcommit' Attack That Hides Malicious Prompts in Images to Hijack AI Coding Agents
  • Security
  • AI Agents
  • Software Dev & Coding

Security researchers have disclosed a new supply-chain attack called "Ghostcommit" that smuggles prompt-injection instructions inside PNG images, slipping past AI code reviewers and tricking coding agents into leaking a repository's secrets. The technique, published on July 11, 2026, as a proof-of-concept by the ASSET Research Group at the University of Missouri-Kansas City, exposes a blind spot in how automated review tools and coding assistants handle non-text files.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 28,064 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year