ainewsblitz.com

Breaking

Oasis Security Finds NemoClaw Weakness That Lets a Webpage Poison Local Ollama Models

  • Security
  • AI Agents

Oasis Security has disclosed a weakness in NVIDIA NemoClaw that can let a single visit to a malicious webpage take unauthenticated control of the local Ollama instance serving an AI agent and plant hidden instructions inside the model's chat template. Those instructions then apply to later conversations, including after the agent supplies its own system prompt. Oasis reported the findings to NVIDIA's Product Security Incident Response Team before publication; as of August 25, 2026, they carry no CVE identifier, no affected-version range, and no patched release, and no exploitation has been reported.

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 27,531 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year