AIPolicyTracker

AI incident ·

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

3 news reports Snapshot 7 Sep 2026

In brief

An AI system built by Meta and Ai Agent System Developers and deployed by Meta, Irregular and 1 other allegedly harmed Targets Of Autonomous Ai Enabled Intrusion Operations.

Risk domain
Not classified
Occurred
Coverage
3 reportsAug 2026

What happened

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.

Laws that address this harm

No recorded instrument yet addresses this use case where it happened. See the open queue.

Matched from the record's risk domain and country to the instruments recorded here. A reviewer can correct the match in the repository (data/external/incident_overrides.yaml).

News reports (3)

Titles link to the original publisher; report text is not reproduced here.

  1. Meta AI model hacks another company during testing
    reuters.com · Rajveer Pardesi, Mrinmay Dey

Who was involved

Alleged harmed party
Targets Of Autonomous Ai Enabled Intrusion Operations

Classification (MIT AI Risk Repository taxonomy)

Risk domain
—
Risk subdomain
—
Causal entity
—
Intent
—
Timing
—
Harm level
—
Sectors
—
Countries
—

Source record: incident #1649 on the AI Incident Database · all 3 reports