Data Exfiltration via Image Rendering Fixed in Amp Code
In this post we discuss a vulnerability that was present in Amp Code from Sourcegraph by which an attacker could exploit markdown driven image rendering to exfiltrate sensitive information. This vulnerability is common in AI applications and agents, and it’s actually similar to one we discussed last year in GitHub Copilot which Microsoft fixed .
Summary from Embrace The Red.
Explained
The technology and terms in this story. Learn more
- ConceptProof of conceptA demonstration that a flaw can be exploited, usually published by researchers.
- AttackPrompt injectionHiding instructions in content an AI reads, so it follows the attacker instead of its user.
- ConceptExploitCode or a technique that turns a software flaw into something an attacker can actually use.
