Topic

Artificial Intelligence: news, advisories and analysis

20 articlesUpdated 6 Oct 2026

CyberSecureToday covers Artificial Intelligence across 20 articles published between 11 Sep 2026 and 6 Oct 2026. The coverage includes 13 vulnerability advisories, 1 incident or breach report and 6 analysis or guidance pieces. 13 advisories are rated critical or high severity, and 1 involves a flaw listed in CISA's Known Exploited Vulnerabilities catalog.

Stories on Artificial Intelligence most often intersect with LLM Security, Prompt Injection and Model Context Protocol, with Technology, Cloud & SaaS the most affected sector. The most recent story, “Why Prompt Guards Cannot Stop Agentic RCE: The Case for MicroVM Isolation in Tool-Calling Pipelines”, was published 6 Oct 2026. Every article is listed below, newest first, with the affected products, severity and remediation guidance in each piece.

Latest coverage

InsightsCloud & SaaS
Why Prompt Guards Cannot Stop Agentic RCE: The Case for MicroVM Isolation in Tool-Calling Pipelines
Recent CVEs in Ollama and AWS MCP reveal that semantic prompt filters cannot prevent tool injection. Engineering teams must isolate agent tools in ephemeral microVMs.
Aisha Noor6 Oct 20268 min read
ThreatsCloud & SaaSHigh
Ollama Patches Experimental Agent Mode Command Injection and Approval Bypass Flaw (CVE-2026-102697)
A security defect in Ollama experimental agent mode allowed command chaining operators to bypass confirmation gates and execute arbitrary shell commands.
Aisha Noor5 Oct 20268 min read
ResearchCloud & SaaS
Self-Replicating AI Worms: Dissecting Autonomous Cross-Agent Prompt Injection Propagation
Researchers demonstrate Morris II style self-replicating adversarial prompt worms propagating autonomously across connected LLM agents and multi-agent workflows.
CST Editorial Desk30 Sep 202612 min read
ResearchCloud & SaaS
Cascading Failure in Multi-Agent AI Swarms: Indirect Prompt Injection Across Autonomous Tool-Calling Pipelines
Deep-dive security research demonstrating how indirect prompt injection exploits Model Context Protocol (MCP) to trigger cascading failures across multi-agent swarms.
Daniel Okafor28 Sep 202612 min read
ThreatsCloud & SaaSHigh
LangChain Core Prompt Template Ingestion Flaw Exposes Host Systems to Path Traversal CVE-2026-34070
A high-severity path traversal vulnerability in langchain-core allows attackers processing untrusted prompt configurations to read arbitrary host filesystem data.
Daniel Okafor28 Sep 20268 min read
ThreatsCloud & SaaSCritical
Code Runner MCP Server Flaw Enables Unauthenticated Remote Code Execution on Hosts
A critical CVSS 9.8 remote code execution vulnerability in Code Runner Model Context Protocol servers permits arbitrary host code execution via untrusted AI agent tool calls.
Daniel Okafor27 Sep 20269 min read
ThreatsCloud & SaaSHigh
Atlassian Model Context Protocol Server Flaws Enable Unauthenticated Arbitrary File Exfiltration CVE-2026-77248
Critical authentication bypass and path traversal vulnerabilities in the Atlassian Model Context Protocol server allow unauthenticated attackers to read and exfiltrate host files.
Daniel Okafor27 Sep 20268 min read
ThreatsCloud & SaaSCritical
Langflow Shareable Playground Flaw Enables Unauthenticated Remote Code Execution
A critical vulnerability in Langflow AI orchestration frameworks allows unauthenticated attackers to execute arbitrary code via insecure component endpoints.
Mei-Lin Chen27 Sep 20269 min read
ThreatsCloud & SaaSCritical
vLLM CUDA Kernel Integer Overflow Leaks Cross-Tenant Inference Prompts
An integer overflow flaw in vLLM PagedAttention CUDA kernels allows concurrent inference requests to read sensitive prompt tokens across multi-tenant GPU memory.
Mei-Lin Chen27 Sep 20269 min read
ThreatsCloud & SaaSCritical
LiteLLM Proxy Request Validation Bypass Exposes Cloud Metadata to SSRF Exploitation CVE-2026-59823
A critical server-side request forgery flaw in LiteLLM AI proxies allows remote attackers to bypass egress restrictions and steal cloud instance credentials.
Aisha Noor27 Sep 20268 min read
ThreatsCloud & SaaSCritical
Dify Cross-Tenant Path Traversal Flaw Exposes Internal Plugin APIs to Unauthorized Access
A critical CVSS 9.4 path traversal flaw CVE-2026-41948 in Dify allows unauthenticated attackers to bypass workspace isolation and invoke internal Plugin Daemon APIs.
Priya Raman25 Sep 202617 min read
ThreatsCloud & SaaSHigh
Open WebUI DNS Rebinding SSRF Exposes Cloud Metadata and Internal Services
A critical TOCTOU race condition flaw CVE-2026-87996 in Open WebUI enables attackers to execute DNS rebinding SSRF attacks and harvest cloud metadata and credentials.
Priya Raman25 Sep 202617 min read
ThreatsCloud & SaaSHigh
Ollama GGUF Parser Integer Overflow Exposes AI Inference Servers to Memory Corruption
A critical integer overflow flaw CVE-2026-86289 in the Ollama GGUF model decoder allows attackers to trigger memory corruption and remote code execution on AI inference clusters.
Priya Raman25 Sep 202616 min read
Cyber AttackBanking & Fintech
CB Financial Services Discloses SEC 8-K Breach Triggered by Shadow AI Use
CB Financial Services files historic SEC Form 8-K Item 1.05 after an employee used an unauthorized AI tool to process non-public customer PII and SSNs.
CST Editorial Desk24 Sep 202615 min read
ThreatsCloud & SaaSHigh
Strands Agents Tools HTTP Request Authorization Flaw Enables Indirect Prompt Injection Credential Theft CVE-2026-18394
AWS resolves high-severity vulnerability CVE-2026-18394 in Strands Agents Tools, where indirect prompt injection forces AI agents to exfiltrate bearer credentials via malicious proxy parameters.
CST Editorial Desk22 Sep 202615 min read
ResearchCloud & SaaS
Agentic AI Security Breakdown: How Indirect Prompt Injections Hijack Autonomous Tool-Calling Agents
Analysis of emerging frontier AI threat vectors: how indirect prompt injections in untrusted documents hijack tool-calling autonomous LLM agents.
Priya Raman17 Sep 202614 min read
ThreatsCloud & SaaSCritical
IBM Langflow Visual AI Framework Remote Code Injection Vulnerability CVE-2026-9198 Exploited in Production Environments
CISA adds CVE-2026-9198 to KEV, warning of active remote code injection attacks weaponizing visual AI workflow builder IBM Langflow in enterprise environments.
Daniel Okafor15 Sep 20269 min read
InsightsCloud & SaaS
OpenAI positions Daybreak as a governed loop for AI-assisted cyber defense
OpenAI says Daybreak combines models, Codex Security and human oversight into a governed loop for inventory, validation, remediation and proof.
Priya Raman12 Sep 20266 min read
ResearchGov & Defence
Anthropic says AI is moving from assistant to orchestrator in cyber operations
Anthropic’s September threat report describes how actors used Claude for reconnaissance, intrusion support, tool rebuilding and parallelized cyber operations.
Mei-Lin Chen12 Sep 20267 min read
ThreatsCloud & SaaSHigh
PaperCut issues superseding maintenance releases as attackers deploy AI agent swarms against 440+ servers
PaperCut shipped consolidated maintenance updates after automated AI agent swarms compromised over 440 print management servers, bypassing earlier emergency hotfixes.
Daniel Okafor11 Sep 20266 min read