DEV Community

# aisecurity

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
LiteLLM CVE-2026-42271 Exploited in the Wild — AI Gateway Flaw Chains to Unauthenticated RCE
vulert_official profile

LiteLLM CVE-2026-42271 Exploited in the Wild — AI Gateway Flaw Chains to Unauthenticated RCE

#litellm #aisecurity #aigateway #vulert
1
Comments
8 min read
We scanned 17,000 Claude Code skills. 39% run shell commands - only 4% say so up front.
skillock profile

We scanned 17,000 Claude Code skills. 39% run shell commands - only 4% say so up front.

#claude #devsecops #aisecurity #opensource
Comments
3 min read
Semantic Kernel CVSS 10.0 Vulnerability: What You Need to Know
nateonline profile

Semantic Kernel CVSS 10.0 Vulnerability: What You Need to Know

#aisecurity #semantickernel #dotnet
Comments
4 min read
AI Agent Finds 21 Zero-Days in FFmpeg for $1,000 — The Economics of Vulnerability Discovery Just Changed
docdavkitty profile
DrMBL

AI Agent Finds 21 Zero-Days in FFmpeg for $1,000 — The Economics of Vulnerability Discovery Just Changed

#ffmpeg #aisecurity #zeroday #depthfirst
Comments
7 min read
Are You Talking to a Bot? Why AI Identity is Harder Than You Think
alessandro_pignati profile

Are You Talking to a Bot? Why AI Identity is Harder Than You Think

#machinelearning #ai #cybersecurity #aisecurity
5
Comments
4 min read
Your AI Agents Are Vulnerable: Understanding and Defending Against RTT Exploits
alessandro_pignati profile

Your AI Agents Are Vulnerable: Understanding and Defending Against RTT Exploits

#ai #machinelearning #cybersecurity #aisecurity
6
Comments
6 min read
How Hackers "Talked" Their Way Into Instagram Accounts: A Case Study in Excessive Agency
alessandro_pignati profile

How Hackers "Talked" Their Way Into Instagram Accounts: A Case Study in Excessive Agency

#ai #cybersecurity #machinelearning #aisecurity
5
Comments 1
3 min read
Anthropic Published a 31.5% Hijack Rate. Most Vendors Won't Even Show You a Number.
agentshield profile

Anthropic Published a 31.5% Hijack Rate. Most Vendors Won't Even Show You a Number.

#aisecurity #llm #promptinjection #mcp
Comments
5 min read
Rem: Remember Everything - Secure Open Source AI Memory
jaychkdsk profile

Rem: Remember Everything - Secure Open Source AI Memory

#aisecurity #opensource #llmsbom #agenticworkflows
Comments
4 min read
The Vatican's Unexpected AI Security Patch: What Developers Need to Know
alessandro_pignati profile

The Vatican's Unexpected AI Security Patch: What Developers Need to Know

#ai #cybersecurity #machinelearning #aisecurity
5
Comments
6 min read
AI Bug Bounty in 2026: 76% More Reports, Programs Shutting Down
dmaxdev profile

AI Bug Bounty in 2026: 76% More Reports, Programs Shutting Down

#aisecurity #bugbounty #opensource #vulnerabilitydiscovery
1
Comments
12 min read
Practical Guide to Preventing Prompt Injection - From an AI Team's Operations Perspective
judy_miranttie profile
Judy

Practical Guide to Preventing Prompt Injection - From an AI Team's Operations Perspective

#promptinjection #aisecurity #aiagentdefense #llmsecurityvulnerabilities
Comments
9 min read
Your Marketing Team Is Now a Software Vendor
michaeltuszynski profile

Your Marketing Team Is Now a Software Vendor

#platformengineering #shadowit #aisecurity #devops
Comments
5 min read
Pinning AI Skill behavior in a lockfile: why hash pinning isn't enough
skillock profile

Pinning AI Skill behavior in a lockfile: why hash pinning isn't enough

#claude #devsecops #aisecurity #opensource
Comments
4 min read
Finding Out What Your AI Agents Actually Got: Discovering Consents and Active Agents in Microsoft Entra
astaykov profile

Finding Out What Your AI Agents Actually Got: Discovering Consents and Active Agents in Microsoft Entra

#ai #entraagentid #aisecurity
2
Comments 1
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.