Vendor
Cursor: Supply chain compromise via Fireworks AI breach
3 TTPsAttackers leveraged a compromised access key from Fireworks AI to gain unauthorized access to Cursor internal systems and inject malicious copies of the Anthropic Claude Code extension into the Cursor VS Code marketplace cache.
Suspicious IDE Extension Installation via VSIX
Threat actors can gain persistence or code execution by sideloading malicious IDE extensions via the VSIX format, often triggered by script hosts or from volatile staging directories.
Anthropic Claude VS Code extension malicious update distribution
11 TTPsAn unknown actor compromised an official Anthropic distribution channel to push a malicious version of the Claude VS Code extension, enabling persistent SSH backdoors and credential theft on developer workstations.
VS Code and Cursor: Credential harvesting by IDE extensions
2 TTPsMalicious extensions or compromised IDE agents may use VS Code or Cursor process trees to exfiltrate multiple sensitive credential stores from a developer workstation.
Suspicious Activity Detection from GenAI Coding Utilities
1 rule 1 TTPThis detection rule identifies suspicious endpoint activity, such as malicious file creation or shellcode execution, originating from or triggered by AI-assisted coding and assistant tools indicating potential supply chain or prompt injection abuse.
GenAI Tool Configuration Poisoning via MCP Server Injection
1 rule 2 TTPsAdversaries are targeting configuration files of popular GenAI tools to inject malicious Model Context Protocol (MCP) servers, enabling persistence, arbitrary command execution, and data exfiltration.
Arbitrary Code Execution in AI Coding Agents via Git Configuration
1 rule 1 TTPMultiple AI coding agents are vulnerable to arbitrary code execution due to the automated, unsandboxed execution of commands defined within a repository's local Git configuration, specifically the 'core.fsmonitor' setting.
Detection of Generative AI Processes Connecting to Unusual Domains
1 rule 1 TTPAdversaries may compromise macOS-based Generative AI (GenAI) tools through prompt injection, malicious Model Context Protocol (MCP) servers, or poisoned plugins to establish Command and Control (C2) channels or exfiltrate sensitive data by causing them to connect to unusual domains.
CVE-2026-63093: Binary Planting Vulnerability in Cursor for Windows
1 rule 3 TTPs 1 CVECVE-2026-63093 describes a binary planting vulnerability in Cursor for Windows version 3.2.16 that allows a remote attacker to achieve arbitrary code execution by placing a malicious `git.exe` file in a crafted repository's root, which the Cursor IDE automatically executes during startup or on a recurring cadence when a developer opens the repository, running the malicious binary under the privileges of the current user.
Security Risks Associated with AI Coding Tools, Including GhostApproval Vulnerability
3 TTPsThe adoption of AI coding tools introduces significant security risks, such as the generation of vulnerable code with OWASP Top 10 flaws, the inadvertent leakage of sensitive secrets and hardcoded credentials, and supply chain compromise via 'slopsquatting,' alongside specific vulnerabilities like 'GhostApproval' which allows remote code execution on developer machines.
Shai-Hulud Campaign Activity
20 IOCsTracking brief for the Shai-Hulud campaign; individual sightings are folded in as reported.
Elastic Defend Alert from GenAI Utility or Descendant
2 rules 1 TTPThis rule detects Elastic Defend alerts originating from or directly related to GenAI coding utilities, indicating potential prompt injection, malicious skills, or supply-chain compromise.
Unsecured Model Context Protocol (MCP) Server Deployments Expose AI Integrations
2 rules 8 TTPs 1 IOCUnsecured Model Context Protocol (MCP) servers, used to connect AI agents to enterprise tools, lack authentication and audit trails, leading to data exfiltration, private repo leaks, cross-tenant exposure, and remote code execution due to AI agents using valid user credentials to make API calls based on potentially poisoned context.
Unusual Modification of GenAI Tool Configuration File
3 rules 4 TTPsThis rule detects unusual modifications to GenAI tool configuration files, potentially indicating an attacker injecting malicious MCP server configurations to hijack AI agents for persistence, command and control, or data exfiltration.