PulseAugur
EN
LIVE 04:53:56

METR reports two security incidents involving API key theft and infrastructure probing

By PulseAugur Editorial · [1 sources] ·

METR experienced two security incidents in early 2026, involving the theft of an API key for public model inference and an attempt to access internal data through an exposed endpoint. While no sensitive information is believed to have been accessed, METR has increased its security investments in response to these near-misses. The organization categorizes its data by sensitivity and has implemented controls to protect confidential information and model access credentials. AI

IMPACT Highlights the ongoing security challenges in managing AI model access and infrastructure, even for organizations focused on evaluation.

RANK_REASON Security incident report from a non-frontier AI lab.

Read on METR (Model Evaluation & Threat Research) →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

METR reports two security incidents involving API key theft and infrastructure probing

How we ranked this

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Security incident report from a non-frontier AI lab.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. METR (Model Evaluation & Threat Research) TIER_1 English(EN) ·

    Update on Security at METR

    <p><strong><em>Please note that this post focuses on incidents where external actors attempted to gain unauthorized access to METR’s systems, not AI agents hacking in our evaluations. We have conducted an initial scan of our evaluations, and currently have no evidence of any agen…

RELATED ENTITIES

RELATED TOPICS