Story
GitLost: We Tricked GitHub's AI Agent into Leaking Private Repos
1 report
1 website
1 discussion
Latest report
Overview
Noma Labs identified a prompt injection vulnerability in GitHub's Agentic Workflows, allowing unauthenticated attackers to access private repository data by posting a crafted GitHub Issue in a public repository within the same organization. This vulnerability has been named GitLost.
Summary from noma.security.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · noma.security
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Read this discussion’s reaction
Based on 5 sampled comments from this thread. Analyzed 2026-07-08.
- Praise: Some commenters see prompt injection as a critical issue that demands robust defenses, paralleling SQL injection vulnerabilities — a call to arms for better AI safety.
- Praise: There's a recognition that organizations need to properly scope LLM access to prevent leaks, hinting at a path forward for responsible AI deployment.
- Concern: Many users are frustrated with large corporations like Microsoft pushing half-baked AI solutions, fearing a breaking point for consumer trust.
- Concern: There's skepticism about GitHub's handling of AI features, with users questioning the responsibility and security of private repositories in the face of these vulnerabilities.
- Concern: The consensus is that misconfiguration and poor scoping of agent permissions led to this vulnerability, highlighting a systemic failure in AI design and governance.