Trendora
vien

Noma

Hold

Platforms

A security company involved in AI agent security research.

Why it's here

Placed in Hold: 1 article(s) of evidence from 2 source(s), led by security coverage, with 0 in the last 30 days. Confidence 32%.

Evidence (1)

  • 8Hacker News·7/8/2026security
    GitLost Shows How GitHub's AI Agent Can Leak Private Repos

    Researchers from Noma and Anthropic reported a security experiment showing that GitHub's AI agent could be manipulated into exposing private repository content. The item highlights agent-security risks in frontier AI systems and the need for stronger safeguards around tool use and data access.