DEV Community

Agent Security Series' Articles

Back to Logan's Series
Prompt Injection Is an Agent Problem, Not a Model Problem
Cover image for Prompt Injection Is an Agent Problem, Not a Model Problem
lkelly profile
Logan for Waxell

Prompt Injection Is an Agent Problem, Not a Model Problem

#ai #security #llm #agents
1
Comments
9 min read
Anthropic Just Leaked Claude Code's Source. Here's What That Means for Every AI Agent You Run.
Cover image for Anthropic Just Leaked Claude Code's Source. Here's What That Means for Every AI Agent You Run.
lkelly profile
Logan for Waxell

Anthropic Just Leaked Claude Code's Source. Here's What That Means for Every AI Agent You Run.

#ai #security #agents #anthropic
Comments
9 min read
Why AI Agents Bypass Human Approval: Lessons from Meta's Rogue Agent Incidents
Cover image for Why AI Agents Bypass Human Approval: Lessons from Meta's Rogue Agent Incidents
lkelly profile
Logan for Waxell

Why AI Agents Bypass Human Approval: Lessons from Meta's Rogue Agent Incidents

#ai #agents #security #governance
Comments
11 min read
The Trusted Document Problem: Why Indirect Prompt Injection Is Now Your AI Agent's #1 Security Risk
Cover image for The Trusted Document Problem: Why Indirect Prompt Injection Is Now Your AI Agent's #1 Security Risk
lkelly profile
Logan for Waxell

The Trusted Document Problem: Why Indirect Prompt Injection Is Now Your AI Agent's #1 Security Risk

#ai #security #agents #openclaw
Comments
9 min read
ForcedLeak: What Salesforce Agentforce's CVSS 9.4 Exploit Reveals About AI Agent Governance
Cover image for ForcedLeak: What Salesforce Agentforce's CVSS 9.4 Exploit Reveals About AI Agent Governance
lkelly profile
Logan for Waxell

ForcedLeak: What Salesforce Agentforce's CVSS 9.4 Exploit Reveals About AI Agent Governance

#ai #security #agents #forcedleak
1
Comments
10 min read
Prompt Injection Doesn't Come from Your Users
Cover image for Prompt Injection Doesn't Come from Your Users
lkelly profile
Logan for Waxell

Prompt Injection Doesn't Come from Your Users

#ai #security #agents #llm
Comments
10 min read
The OpenClaw Security Crisis: 135,000 Exposed AI Agents and the Runtime Governance Gap
Cover image for The OpenClaw Security Crisis: 135,000 Exposed AI Agents and the Runtime Governance Gap
lkelly profile
Logan for Waxell

The OpenClaw Security Crisis: 135,000 Exposed AI Agents and the Runtime Governance Gap

#openclaw #ai #security #agents
Comments
12 min read
340% and Climbing: What the CIS Prompt Injection Report Means for Enterprise AI Agents
Cover image for 340% and Climbing: What the CIS Prompt Injection Report Means for Enterprise AI Agents
lkelly profile
Logan for Waxell

340% and Climbing: What the CIS Prompt Injection Report Means for Enterprise AI Agents

#security #ai #agents #llm
Comments
10 min read
600 Firewalls in 5 Weeks: What the FortiGate AI Attack Teaches Us About Human Oversight
Cover image for 600 Firewalls in 5 Weeks: What the FortiGate AI Attack Teaches Us About Human Oversight
lkelly profile
Logan for Waxell

600 Firewalls in 5 Weeks: What the FortiGate AI Attack Teaches Us About Human Oversight

#fortigate #ai #arx0n #mcp
1
Comments
10 min read
Comment and Control: The GitHub AI Agent Attack That Three Vendors Hushed
Cover image for Comment and Control: The GitHub AI Agent Attack That Three Vendors Hushed
lkelly profile
Logan for Waxell

Comment and Control: The GitHub AI Agent Attack That Three Vendors Hushed

#github #ai #claude #gemini
2
Comments
10 min read