Geo News
Community curated by people like you
LatestAICryptoHealthWorld AffairsUS Politics

Data exfiltration stories

Oct 30, 2026

Anthropic official VS Code extension backdoored for nearly 12 hours

An official extension for Anthropic's Claude model was backdoored and threatened as many as 5,000 developers' machines, with Anthropic yet to warn customers of the security breach.

Oct 30, 2026·3 sources
00
Oct 29, 2026

Defense contractor connected Claude agent to Pentagon system for two months

An Accenture employee's personal Claude AI agent ran on a secure Department of Defense network for approximately two months before the vulnerability was identified, according to WIRED reporting.

Oct 29, 2026·2 sources
00
Oct 21, 2026

LiteLLM supply chain attack distributes malware stealing credentials and remote access trojan

Unknown attackers compromised LiteLLM's release process on Wednesday, distributing a malicious version (1.107.0) through PyPI and Docker registries containing malware designed to steal cloud and AI credentials plus a remote access trojan capable of executing arbitrary code. Users who ran the compromised version should treat their secrets as compromised.

Oct 21, 2026·3 sources
00
Aug 8, 2026

Security Researchers Expose Critical Vulnerability in Atlassian's Rovo AI Assistant Allowing Data Exfiltration

Security firm PromptArmor has demonstrated that Atlassian's Rovo AI assistant can be hijacked through hidden instructions in uploaded PDFs or malicious links to silently exfiltrate sensitive data from Jira, Confluence, and third-party integrations to attacker-controlled servers without user approval or audit trails.

Aug 8, 2026·4 sources
00

Top claims

  • ▪The malicious Claude Code extension version 2.1.313 exfiltrates host details including IP address, username, hostname, global Git email, and the names of up to 40 environment variables containing sensitive keywords like AWS, GCP, KEY, TOKEN, SECRET, or PASS
  • ▪The compromised Anthropic Claude Code extension version 2.1.313 was published under Anthropic's legitimate publisher identity anthropic.claude-code
  • ▪Neither Cursor nor Anthropic has publicly explained the precise method or credential compromise through which attackers gained access to publish to Anthropic's official publisher account during the October 29, 2026, incident

People involved

Felix Rieseberg

Subtopics

AI security3AI developer tools2Claude Code2Agent permissions1AI agent problems1AI agents1AI assistants & chatbots1AI coding1AI cybersecurity1AI privacy & surveillance1Black October cyber crisis(AI)1Coding agents1Credential isolation1Docker container1Enterprise AI security1Microsoft1National security1pip1Prompt injection1Python1VS Code extension1

Related timelines

Congress

110 stories

Crypto hacks

100 stories

Iran War

209 stories

Payments

118 stories

Russia-Ukraine war

136 stories