Incident 1649: Meta AI Model Reportedly Exploited Security Vulnerability in Real Third-Party Service During Cybersecurity Evaluation

Description: During a Meta cybersecurity evaluation conducted with Irregular, one of Meta's AI models reportedly gained unintended Internet access after an evaluation-environment misconfiguration and exploited a vulnerability in a real third-party service. The model was reportedly identified as Muse Spark 1.1, although Meta had not publicly confirmed that identification or the fuller account of what occurred inside the affected company.

Tools

New ReportNew ResponseDiscoverView History

Entities

View all entities
Alleged: Meta and AI agent system developers developed an AI system deployed by Meta , Irregular and AI agent system deployers, which harmed Targets of autonomous AI-enabled intrusion operations.
Alleged implicated AI systems: Muse Spark 1.1 and AI agent systems

Incident Stats

Incident ID
1649
Report Count
3
Incident Date
2026-08-05
Editors
Daniel Atherton
Loading...
Meta AI model hacks another company during testing
reuters.com · 2026

Aug 5 (Reuters) - Meta said on Wednesday one of its AI models hacked another company during cybersecurity testing, fanning concerns about how developers can contain increasingly capable AI systems after similar incidents ‌at rivals Anthropi…

Loading...
Meta AI model hacked a company during misconfigured cyber test
bleepingcomputer.com · 2026

Meta has become the latest AI company to confirm that one of its models hacked a real organization during cybersecurity testing, as similar incidents continue to emerge following OpenAI'sOpenAI's initial disclosure that its agents breached …

Loading...
AI models are breaking out of their cages. Their creators are scrambling.
washingtonpost.com · 2026

SAN FRANCISCO --- Staff members at ChatGPT maker OpenAI didn't notice for weeks after their AI systems made a chilling leap this spring.

Instead of answering questions designed to test their cybersecurity capabilities, a group of AI models…

Variants

A "variant" is an AI incident similar to a known case—it has the same causes, harms, and AI system. Instead of listing it separately, we group it under the first reported incident. Unlike other incidents, variants do not need to have been reported outside the AIID. Learn more from the research paper.
Seen something similar?

Similar Incidents

Selected by our editors

Claude Opus 4.7 Reportedly Compromised Real Company's Production Infrastructure During Cybersecurity Evaluation

· 14 reports

Claude Mythos 5 Reportedly Published Malicious PyPI Package That Compromised Real Security Company During Evaluation

· 14 reports

Anthropic Research Model Reportedly Scanned 9,000 Targets and Compromised Real Company's Application During Evaluation

· 14 reports

Anthropic and OpenAI AI Agents Reportedly Took Unsanctioned Actions on the Live Internet During UK AISI Cybersecurity Evaluations

· 3 reports
By textual similarity

Did our AI mess up? Flag the unrelated incidents

Loading...
Fake LinkedIn Profiles Created Using GAN Photos

Fake LinkedIn Profiles Created Using GAN Photos

· 4 reports
Loading...
Warehouse robot ruptures can of bear spray and injures workers

Warehouse robot ruptures can of bear spray and injures workers

· 17 reports
Loading...
Tesla Model X on Autopilot Crashed into California Highway Barrier, Killing Driver

Tesla Model X on Autopilot Crashed into California Highway Barrier, Killing Driver

· 14 reports
Previous Incident