Indirect Prompt Injection Exploits GitHub's AI Agent to Leak Private Repository Data
GitHub's AI agents just became a vector for stealing private code. Here's how attackers exploited prompt injection to leak confidential repos.
Why it matters
Prompt injection vulnerabilities in agentic AI systems represent a critical security governance issue for enterprises deploying autonomous agents at scale. This real-world exploit demonstrates that AI safety considerations must extend beyond model training to production workflow architecture.
The key facts
7 to knowExploit name: GitLost
Vector: Indirect prompt injection via public GitHub issues
Target: GitHub Agentic Workflows
Impact: Private repository data leakage to public comments
Discovery source: Noma Security
Attack method: Concealed instructions embedded in public issues bypass AI agent security safeguards
Published: July 23, 2026
Go to the source
InfoQ AI/MLinfoq.com
Publisher excerpt: GitLost is a prompt-injection exploit discovered by Noma Security that tricks GitHub's new Agentic Workflows into leaking private data. By embedding concealed instructions within public GitHub issues, attackers can circumvent security safeguards and induce AI agents to reveal confidential…