AI vulnerabilities
What has actually happened, stated accurately
Each case says what kind of event it was. A controlled evaluation is not a breach, and a vendor disrupting misuse of its own product is not an agent escaping control. The distinction is the point: risk you can assess is more useful than risk you are alarmed by.
CONFIRMED INTRUSION
Hugging Face, July 2026: an autonomous agent ran the intrusion end to end
A malicious dataset chained two code-execution paths into node-level access and lateral movement across internal clusters, driven by an attacker framework that executed roughly 17,000 individual actions.
CONFIRMED INTRUSION
Vercel, April 2026: a small third-party AI tool became everyone's problem
An attacker compromised Context.ai, then used an employee's Google Workspace OAuth grant to reach Vercel's internal systems and decrypt non-sensitive environment variables.
SUPPLY CHAIN COMPROMISE
LiteLLM, March 2026: a compromised scanner poisoned an AI gateway
TeamPCP compromised the Trivy CI pipeline, used that access to obtain LiteLLM's PyPI publishing tokens, and shipped a credential stealer in two releases of a package with roughly 95 million monthly downloads.
COORDINATED DISCLOSURE
Opening a repository was enough: pre-trust execution in a coding agent
A repository-controlled config file made a coding agent run attacker commands before its own trust dialog appeared, turning cloning a project into code execution.
CONTROLLED EVALUATION
OpenAI Operator: indirect prompt injection becomes an action risk
OpenAI’s published red-team work shows how untrusted content can influence a browser-using agent that can operate tools or move data.
CONTROLLED EVALUATION
Anthropic’s agentic-misalignment evaluation: model access can resemble an insider threat
Anthropic’s fictional corporate simulations test what can happen when a tool-using model has sensitive context, external actions, and a deliberately constructed goal conflict.
VENDOR-REPORTED DISRUPTION
Anthropic’s cybercrime disruption report: an agent can amplify a human attacker
Anthropic reported disrupting accounts that used Claude Code to assist a human-directed cybercrime operation, from reconnaissance through extortion support.
COORDINATED DISCLOSURE
nullifAI: malicious PyTorch models evaded pickle scanning on Hugging Face
Researchers found two Hugging Face-hosted model files with malicious pickle payloads that could reach web shells when loaded in an unsafe environment.
Every case links to the originating organization rather than to coverage of it. Where a finding comes from a controlled evaluation, the page says so.