Curated Cyber Threat Intelligence

Threat Feed

Daily intelligence on vulnerabilities, threat actors and geopolitical context — distilled from primary sources.

scheduleUpdated 2026-09-04 · 02:17 UTC
articleTotal: 1172 reports

Filtered Reports

10 / 10 results
Active filter:tag: #anthropic✕ clear
OpenAI, Anthropic, Google reasoning APIs leaked secrets via session replayhighbug_reportVulnerability
bug_reportVulnerability

OpenAI, 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.

OpenAI12 Aug · 09:47 UTC
Claude AI Model Uploads Malicious PyPI Package During Security Evaluationhighperson_alertThreat Actor
person_alertThreat Actor

Claude 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.

Anthropic30 Jul · 22:57 UTC
Ruflo AI orchestration platform RCE allows full system compromise via MCPcriticalbug_reportVulnerability
bug_reportVulnerability

Ruflo 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.

CVE-2026-5972629 Jul · 13:39 UTC
Bing malvertising pushes fake Claude installer delivering SectopRAThighbug_reportVulnerability
bug_reportVulnerability

Bing 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.

Microsoft23 Jul · 17:48 UTC
Claude Cowork sandbox escape lets AI agent access macOS host fileshighbug_reportVulnerability
bug_reportVulnerability

Claude 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.

Anthropic23 Jul · 11:27 UTC
AI browsers leak credentials via BioShocking social engineering attackhighbug_reportVulnerability
bug_reportVulnerability

AI 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.

OpenAI30 Jun · 06:37 UTC
US orders Anthropic to restrict foreign access to advanced AI modelshighpublicGeopolitical
publicGeopolitical

US 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.

Anthropic13 Jun · 08:01 UTC
U.S. orders Anthropic to suspend foreign access to advanced AI modelshighpublicGeopolitical
publicGeopolitical

U.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.

Anthropic13 Jun · 03:42 UTC
Prompt injection in Claude Code GitHub Action exposes workflow secretshighbug_reportVulnerability
bug_reportVulnerability

Prompt 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.

Anthropic5 Jun · 14:46 UTC
Malicious npm package targets Claude AI user data directoryhighbug_reportVulnerability
bug_reportVulnerability

Malicious 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.

npm27 May · 13:44 UTC