Chrome Extension Returns with Malicious Intent After Removal
A Chrome extension removed for stealing AI chats returned to the Web Store and resumed malicious activities — immediate remediation recommended.
§Topic · AI & LLM Security
AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesWednesday, August 12
Monday, August 10
Critical Vulnerabilities in Claude Code and Gemini CLI Expose CI Workflow Secrets
PremiumFlaws in Claude Code and Google's Gemini CLI let an unprivileged GitHub issue execute code on CI runners and expose secrets.
Atlassian's Rovo AI Vulnerability Risks Enterprise Data Exposure
PremiumVaronis found a one-click RovoBlast vulnerability that could expose Confluence, Jira and SharePoint data to attackers.
Exposed OT Controllers and Foreign Telecoms Pose Persistent Security Risks
PremiumSANS NewsBites flags exposed OT controllers after water attacks, Chinese telecoms' US presence, and OSAA's SAFE proposal for AI findings sharing.
Friday, August 7
Security Researcher Uncovers Vulnerability in ChatGPT's Sandbox Environment
PremiumResearcher demonstrated a PoC providing C2-style influence over ChatGPT's isolated sandbox, highlighting container escape risks.
AI Coding Agents Expose Critical Vulnerabilities
PremiumRepeatable vulnerabilities across Anthropic, Google, and OpenAI coding agents allow RCE, API credential theft, and supply-chain compromise.
Get these articles delivered to your inbox.
Subscribe free