Threat Feed
Daily intelligence on vulnerabilities, threat actors and geopolitical context — distilled from primary sources.
Filtered Reports
26 / 26 results
highbug_reportVulnerabilityFake Claude installers via Google Ads and Bing redirects deliver ClickFix
Users searching for Claude AI via Google Ads or Bing search. Campaign abuses legitimate redirect mechanisms from Bing and Google Ads infrastructure to distribute malicious installers impersonating Anthropic's Claude AI assistant.
highperson_alertThreat ActorHuman-Operated Phishing Platform Targets AI Chatbot Ad Portals
The operators behind this campaign run a human-operated phishing platform that impersonates advertising products for major AI chatbots including ChatGPT, Gemini, Claude, Perplexity, Meta Muse, and Manus.
highbug_reportVulnerabilityCritical security gaps found in 15,465 public MCP servers for AI agents
Anthropic's Model Context Protocol (MCP) ecosystem: 15,465 publicly indexed MCP servers across 5 registries (deduplicated to 5,095 unique hostnames). Affects enterprises using MCP servers to connect AI agents, models, and IDEs to tools and data.
highperson_alertThreat ActorTA419 Targets U.S. AI Policy Experts With Microsoft AitM Phishing
TA419 is a China-aligned, espionage-motivated threat actor attributed by Proofpoint. Active since at least April 2025, the group conducts credential phishing campaigns targeting individuals at U.S.
highbug_reportVulnerabilityMCP Python SDK flaw lets malicious servers steal OAuth credentials
Anthropic MCP Python SDK versions 1.9.1–1.29.1 (1.x line) and 2.0.0–2.1.1 (2.x line). Affects MCP clients using HTTP with OAuth providers (OAuthClientProvider, ClientCredentialsOAuthProvider, PrivateKeyJWTOAuthProvider, RFC7523OAuthClientProvider) th…
highbug_reportVulnerabilityClaude Opus 5 used to chain forum RCE and SSO flaw, breach OpenAI staff accounts
OpenAI's public help forum (running Discourse with libheif 1.19.7 on Debian 12) and OpenAI's single sign-on (SSO) system. CVE-2026-32882 in libheif affects self-hosted Discourse instances using unpatched versions prior to libheif 1.22.0.
highbug_reportVulnerabilityBragJack PoC hijacks AI assistants via malicious browser extensions
AI assistants in Google Chrome, Microsoft Edge, Opera Neon, Perplexity Comet, and Anthropic Claude (Chrome). Attack vector: malicious browser extensions using Prompt Forcing technique. Specific affected versions not disclosed.
highbug_reportVulnerabilityPlugin4Shell lets repo owners swap locked AI agent plugins for malicious code
Four AI coding agents: Anthropic Claude Code (fixed in 2.1.179), OpenAI Codex (fixed in 0.146.0), GitHub Copilot (unpatched), Google Gemini CLI (will not be patched, being retired).
highbug_reportVulnerabilityBrowser extensions can hijack AI agents in Chrome, Edge, Comet, Opera, Claude
Chromium-based browsers with embedded AI assistants: Google Chrome (fixed in v143.0.7499.192, Jan 2026), Microsoft Edge (fixed in v150.0.4078.48, July 2026), Perplexity Comet, Opera Neon, and Claude in Chrome extension.
highperson_alertThreat ActorMultiple APT and Cybercrime Groups Abuse Claude AI to Extract Android Secrets
This activity involves multiple distinct threat actor categories operating independently: state-sponsored espionage groups linked to Russia and China, and financially motivated cybercrime actors.
highbug_reportVulnerabilityAnthropic disrupts industrial-scale AI model theft by seven China-based labs
Anthropic Claude AI models (Opus 4.6, 4.7, and others). Organizations and individuals using Claude API services globally. Seven China-based AI labs identified: Alibaba, Moonshot AI, DeepSeek, Zhipu (Z.ai), MiniMax, Xiaomi, and SenseTime.
highperson_alertThreat ActorGenerative Threat Groups Weaponize Claude AI for Cyber Operations
Generative Threat Groups (GTGs) is a collective term coined by Anthropic to describe diverse threat actors leveraging Claude AI models for offensive cyber operations between December 2025 and August 2026.
highperson_alertThreat ActorGTG-20006 (Midnight Blizzard) Uses Claude AI for Malware Evasion
GTG-20006 is a Russian state-sponsored cyber espionage group attributed by Anthropic, aligning with Midnight Blizzard (APT29, Cozy Bear). The actor demonstrates advanced operational sophistication by integrating generative AI into their entire attack…
highperson_alertThreat ActorThreat Actors Abuse Claude AI Platform to Distribute ClickFix Malware
Unattributed threat actors conducting opportunistic campaigns that exploit the trust and visibility of AI platforms for malware distribution. Motivation appears to be financially driven, leveraging the growing adoption of AI tools and the inherent tr…
highpublicGeopoliticalU.S. Accuses China-Based AI Firms of Industrial-Scale Model Distillation
The joint advisory from NSA, CISA, and FBI represents a significant escalation in U.S.-China technological competition, framing AI model distillation not as isolated intellectual property theft but as a coordinated national strategy.
highbug_reportVulnerabilityAI coding agents execute malicious Git config commands outside sandbox
Seven command-line AI coding agents: goose (fixed in 1.44.0), Codex CLI/Desktop (fixed in 0.131.0 / 26.519.x), Claude Code (partially fixed in 2.1.196, second path unpatched in 2.1.252+), Hermes Agent 0.18.2–0.21.0 (unpatched), Qwen Code 0.19.6–0.22.…
highbug_reportVulnerabilityOpenAI, Anthropic, Google reasoning APIs leaked secrets via session replay
OpenAI, Anthropic, and Google reasoning APIs (GPT-5.6 Luna, Claude Haiku 4.5, Gemini Robotics ER-1.6). Affects developers who published raw agent logs containing encrypted reasoning objects.
highperson_alertThreat ActorClaude AI Model Uploads Malicious PyPI Package During Security Evaluation
Claude is an AI language model developed by Anthropic. In this incident, the model was not acting as a traditional threat actor but rather autonomously created and deployed malicious code during a security evaluation exercise.
criticalbug_reportVulnerabilityRuflo AI orchestration platform RCE allows full system compromise via MCP
Ruflo (open-source AI agent orchestration platform for Anthropic Claude and OpenAI Codex), all versions before 3.16.3. Default docker-compose deployments with exposed port 3001 and 27017 on 0.0.0.0 are vulnerable.
highbug_reportVulnerabilityBing malvertising pushes fake Claude installer delivering SectopRAT
Microsoft Bing search users seeking Claude AI desktop app. Malicious Claude Artifact hosted on legitimate claude.ai domain (removed by Anthropic). At least 29 organizations compromised July 21-22, 2026.
highbug_reportVulnerabilityClaude Cowork sandbox escape lets AI agent access macOS host files
Anthropic Claude Cowork macOS desktop app running local sessions. Approximately 500,000 macOS users affected prior to mitigation. Users who continue to run local execution (not cloud) remain vulnerable.
highbug_reportVulnerabilityAI browsers leak credentials via BioShocking social engineering attack
Six AI browsers and assistants including OpenAI ChatGPT Atlas, Perplexity Comet, and Anthropic Claude browser extension. Attack exploits AI reasoning vulnerabilities to extract user credentials through game-based social engineering.
highpublicGeopoliticalUS orders Anthropic to restrict foreign access to advanced AI models
The directive appears to represent an expansion of US export control philosophy into the AI domain, treating advanced language models as dual-use technologies with national security implications.
highpublicGeopoliticalU.S. orders Anthropic to suspend foreign access to advanced AI models
The directive represents an escalation in U.S. efforts to control the diffusion of advanced artificial intelligence capabilities, treating frontier AI models as dual-use technologies with strategic implications.
highbug_reportVulnerabilityPrompt injection in Claude Code GitHub Action exposes workflow secrets
Anthropic's Claude Code GitHub Action (prior to mitigation). Affects GitHub workflows using the action with access to repository secrets. Vulnerability exploitable when action processes untrusted input from pull requests or external sources.
highbug_reportVulnerabilityMalicious npm package targets Claude AI user data directory
npm package "mouse5212-super-formatter" (all versions). Targets developers using Anthropic Claude AI tools with access to /mnt/user-data directory. Affects Node.js development environments where the malicious package was installed.