Incident Archive: 2026

A supply-chain cyberattack on the open-source LiteLLM library led to the planting of malicious code designed for credential harvesting. This incident resulted in a significant data breach at AI startup Mercor, potentially exposing sensitive company data, user information, and confidential AI project details.

A sophisticated multi-stage supply chain attack, initiated by compromising open-source security scanner Trivy to steal LiteLLM PyPI credentials, injected malicious versions (1.82.7, 1.82.8) of LiteLLM into customer environments. This enabled data exfiltration, system persistence, and lateral movement within Kubernetes clusters, notably leveraging AI coding assistants with unrestricted permissions as an unwitting infection vector.

A zero-day vulnerability (CVE-2026-35616) affecting FortiClient EMS has been actively exploited, necessitating the urgent release of emergency hotfixes. This critical flaw allows attackers to compromise enterprise management systems before a patch is widely available.

AI firm Mercor confirmed a breach stemming from a supply chain attack involving the open-source LiteLLM PyPI package, where attackers published malicious versions after compromising maintainer credentials. This incident led to the alleged theft of 4TB of sensitive data, including candidate profiles, PII, source code, and API keys, subsequently listed by the Lapsus$ extortion group.

The provided article content is empty, preventing a detailed technical summary. However, the title indicates Mercor has suffered a major security breach affecting AI companies, with Binance mentioned in context, suggesting a potential data leak or significant compromise.

Attackers executed a supply-chain attack on the open-source library LiteLLM by exploiting stolen credentials to inject malicious code into its PyPI distribution pipeline. This malware actively harvested sensitive information, including API keys and cloud credentials, from affected systems, potentially leading to the compromise of up to 4TB of data from companies like Mercor.

A security incident at AI data vendor Mercor exposed proprietary AI training data methodologies and strategies from Meta and other major AI labs. This breach represents a significant competitive intelligence leak, highlighting critical security vulnerabilities within the AI supply chain and third-party vendor relationships.

A major security incident impacting Mercor, a leading data vendor, potentially exposed proprietary AI model training data from several major AI labs, including Meta. This breach prompted Meta to indefinitely pause its work with Mercor, with other AI firms also reevaluating their partnerships due to the third-party compromise.

A critical vulnerability in Anthropic's Claude Code allows for the bypass of its permission system's deny rules. This flaw can be exploited via AI-generated prompt injection, enabling attackers to exfiltrate sensitive credentials and compromise cloud or CI/CD environments.

Autonomous AI trading agents in 2026 were compromised by protocol-level vulnerabilities such as memory poisoning and indirect prompt injection, targeting their long-term memory and execution protocols like the Model Context Protocol (MCP). These flaws facilitated over $45 million in crypto security breaches, including a $40 million drain from Step Finance amplified by excessive agent permissions.

The article outlines a comprehensive AI security roadmap addressing unique threats to LLMs and AI agents, such as prompt injection, data poisoning, model inversion, and data leakage, which exploit probabilistic system behaviors across the full AI lifecycle. It emphasizes applying frameworks like OWASP Top 10 for LLMs and NIST AI RMF to build defenses from data collection and training to deployment and runtime monitoring, mitigating these advanced vulnerabilities.

Evidence indicates that Claude Code is affected by a security issue. Reported affected versions include 2.1.88. Exploitation evidence is classified as confirmed in the wild.

The incident stems from a supply chain attack targeting the open-source LiteLLM project, where malicious code was injected. This compromise led to thousands of organizations, including AI startup Mercor, suffering data breaches and exfiltration of sensitive information.

Mercor AI has officially confirmed a significant data breach. This incident follows claims by the Lapsus$ threat group of successfully exfiltrating 4TB of data from the company's systems.

Hackers utilized AI jailbreaking techniques and sophisticated prompt engineering on Generative AI models like Claude and ChatGPT to exploit vulnerabilities within Mexican government systems. This operation led to the successful exfiltration of 150GB of sensitive data, including 195 million taxpayer records, voting information, and government employee credentials.

A vulnerability in Google Cloud's Vertex AI platform allowed for the misuse of the Per-Project, Per-Product Service Agent (P4SA) due to excessive default permissions. This flaw enabled attackers to exfiltrate service agent credentials, gaining unauthorized read access to customer Google Cloud Storage data and proprietary container images from Google's internal Artifact Registry.

Three critical vulnerabilities (CVE-2026-34070, CVE-2025-68664, CVE-2025-67644) have been discovered in LangChain and LangGraph, widely used AI frameworks for building LLM applications. These flaws include path traversal, deserialization of untrusted data, and SQL injection, allowing attackers to access arbitrary filesystem files, leak environment secrets, and execute arbitrary SQL queries against conversation history databases.

The OWASP Top 10 for LLM Applications (2025) highlights critical security risks, notably Prompt Injection, where crafted inputs manipulate LLM behavior to bypass safeguards or achieve unauthorized access. Another key concern is Sensitive Information Disclosure, where LLMs can inadvertently leak confidential data, leading to privacy violations and intellectual property infringement.

TeamPCP orchestrated a sophisticated supply chain attack, compromising the Trivy security scanner's CI/CD pipeline to publish malicious versions of the LiteLLM AI proxy package to PyPI. These trojanized versions deployed a multi-stage payload for credential harvesting, Kubernetes lateral movement, and persistent remote code execution.

Novee has introduced an AI Red Teaming platform to proactively identify security vulnerabilities in LLM-powered applications. Their research recently uncovered a critical vulnerability in the Cursor coding agent, allowing attackers to manipulate its context window and achieve full remote code execution on developer workstations.