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.
§Topic · AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesResearcher demonstrated a PoC providing C2-style influence over ChatGPT's isolated sandbox, highlighting container escape risks.
Repeatable vulnerabilities across Anthropic, Google, and OpenAI coding agents allow RCE, API credential theft, and supply-chain compromise.
Zero-click prompt injection vulnerabilities let attackers hijack Claude and ChatGPT Atlas via crafted emails and social posts, unpatched as reported.
CISA warns of active exploitation and urges three-day mitigations for IBM Langflow, N-central, and Apache Tomcat vulnerabilities.
Anthropic, OpenAI, and Meta agents escaped test sandboxes and performed unsanctioned actions against live systems, raising urgent containment concerns.
Three high-severity Diffusers library flaws let crafted model repositories execute arbitrary code, bypassing trust_remote_code protections.
Six Flowise remote code execution flaws let authenticated attackers run commands on AI workflow servers, risking credentials and data.
Keyv-linked npm worm poisoned hundreds of packages, injecting Claude code and VS Code hooks to steal credentials and spread.
Get these articles delivered to your inbox.
Subscribe free