Home/Tag/Llm

Llm

6 articles tagged with "Llm"

Malware4 min read

Attackers Deploy LLM Agent for Post-Exploitation in Marimo Attack

Sysdig documents the first AI-agent-driven intrusion: attackers exploited Marimo CVE-2026-39987, then used an LLM agent to pivot through AWS and exfiltrate a PostgreSQL database in under an hour.

Malware DeskMay 30, 2026

Vulnerabilities3 min read

LiteLLM SQL Injection Exploited 36 Hours After Disclosure—CISA Issues Deadline

CVE-2026-42208, a CVSS 9.3 pre-auth SQL injection in the LiteLLM LLM gateway, was weaponized within 36 hours of disclosure. CISA added it to KEV with a May 11 federal deadline.

Vulnerability DeskMay 11, 2026

Vulnerabilities4 min read

LMDeploy SSRF Exploited 12 Hours After Disclosure

CVE-2026-33626 in LMDeploy AI toolkit was weaponized within 12 hours of publication, targeting AWS credentials and internal services. Patch to v0.12.3 immediately.

Vulnerability DeskApr 24, 2026

Vulnerabilities4 min read

WeKnora AI Framework Hit with Twin CVSS 9.9 RCE Flaws

Critical command injection and SQL bypass vulnerabilities in Tencent's WeKnora LLM framework allow unauthenticated RCE. Patch to versions 0.2.10 and 0.2.12 now.

Vulnerability DeskMar 8, 2026

Tools4 min read

Cisco's ACE Framework Cuts LLM Token Costs by Up to 90%

Analytics Context Engineering addresses three failure modes when LLMs process machine data, delivering dramatic token savings and accuracy gains.

ProbablyPwned Editorial TeamFeb 4, 2026

Threat Intelligence4 min read

Attackers Mapped 91,000+ AI Endpoints in Mass Recon Campaign

GreyNoise honeypot data reveals coordinated reconnaissance of LLM infrastructure including OpenAI, Claude, and Ollama deployments over 11 days.

Threat Intel DeskJan 14, 2026