DEV Community

#agents

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your AI agent's guardrails don't know what it's allowed to do
pqbuilder profile
German

Your AI agent's guardrails don't know what it's allowed to do

#security #webdev #ai #agents
Comments
5 min read
Microsoft confie 90 % de sa chasse aux failles à un mini-modèle
thibault_monteiro profile

Microsoft confie 90 % de sa chasse aux failles à un mini-modèle

#agents #ai #cybersecurity #microsoft
Comments
6 min read
Agent Identity Spoofing in Multi-Agent Systems: Your Orchestrator Has No Idea Who It Is Talking To
rxkov profile
Rxkov

Agent Identity Spoofing in Multi-Agent Systems: Your Orchestrator Has No Idea Who It Is Talking To

#agents #architecture #cybersecurity #security
Comments 1
5 min read
Stateless AI agents are a bug, not a feature. Meet the Brain Flywheel.
itaisagi profile
Itai

Stateless AI agents are a bug, not a feature. Meet the Brain Flywheel.

#ai #agents #buildinpublic #indiehackers
Comments
6 min read
When an AI Agent Makes a Mistake in Production, Which Layer Should Stop It?
hosseinhezami profile

When an AI Agent Makes a Mistake in Production, Which Layer Should Stop It?

#ai #agents #tutorial #production
6
Comments 3
15 min read
AI Agents Are eval(userInput) With Extra Steps
rxkov profile
Rxkov

AI Agents Are eval(userInput) With Extra Steps

#agents #ai #llm #security
Comments
5 min read
AI Agent Observability Is Off by Default — And That Is a Security Problem
rxkov profile
Rxkov

AI Agent Observability Is Off by Default — And That Is a Security Problem

#agents #ai #monitoring #security
Comments 2
5 min read
AI Agent Replay Attacks: Your Execution Trace Is a Durable Attack Surface
rxkov profile
Rxkov

AI Agent Replay Attacks: Your Execution Trace Is a Durable Attack Surface

#agents #ai #cybersecurity #security
Comments
5 min read
Tool Grants Are Firewall Rules: How Excessive Agency Turns Permitted Actions Into Production Incidents
rxkov profile
Rxkov

Tool Grants Are Firewall Rules: How Excessive Agency Turns Permitted Actions Into Production Incidents

#agents #ai #llm #security
Comments
4 min read
Agent Output Is an Injection Vector: SQL, Shell, and Template Engines
rxkov profile
Rxkov

Agent Output Is an Injection Vector: SQL, Shell, and Template Engines

#agents #ai #cybersecurity #llm
Comments
5 min read
From UX to AX: Why I Think We’re Not Just Redesigning Interfaces, We’re Redesigning Trust
kirankrishnap profile

From UX to AX: Why I Think We’re Not Just Redesigning Interfaces, We’re Redesigning Trust

#ai #agents #uxdesign #user
Comments
6 min read
Docker Sandboxes for AI Agents: The Right Way to Isolate Untrusted Code Execution
rxkov profile
Rxkov

Docker Sandboxes for AI Agents: The Right Way to Isolate Untrusted Code Execution

#agents #ai #docker #security
Comments
5 min read
A multi-agent translation pipeline: 1,081 documents at $2.31 each
jackhomer profile

A multi-agent translation pipeline: 1,081 documents at $2.31 each

#ai #agents #llm #translation
Comments
2 min read
AI Agent Tool-Chaining: When Individually Permitted Calls Compose Into Unauthorized Capability
rxkov profile
Rxkov

AI Agent Tool-Chaining: When Individually Permitted Calls Compose Into Unauthorized Capability

#agents #ai #cybersecurity #security
Comments
4 min read
AI Agent HTTP Tools Are SSRF by Construction: Network Policy Is the Only Real Control
rxkov profile
Rxkov

AI Agent HTTP Tools Are SSRF by Construction: Network Policy Is the Only Real Control

#agents #ai #cybersecurity #security
Comments 1
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.