DEV Community

#promptinjection

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Your AI Feature Is Now Part of Your Attack Surface
ikilic profile

Your AI Feature Is Now Part of Your Attack Surface

#ai #cybersecurity #llm #promptinjection
Comments
9 min read
OpenAPA: una vecchia idea militare per bloccare la prompt injection negli agenti (senza nuovi chip)
frontendfacile profile

OpenAPA: una vecchia idea militare per bloccare la prompt injection negli agenti (senza nuovi chip)

#promptinjection #agentillm #sicurezzatool #policydiclassificazi
Comments
3 min read
Meta cambia rotta (di nuovo): Muse e l’era dell’agente personale sempre con te
frontendfacile profile

Meta cambia rotta (di nuovo): Muse e l’era dell’agente personale sempre con te

#agentiai #privacyesicurezza #promptinjection #sandboxevm
Comments
4 min read
AURA v0.1.0: Deterministic Trigger Extraction, Auditable Math & a Self-Healing Analytics Engine
kate8382 profile

AURA v0.1.0: Deterministic Trigger Extraction, Auditable Math & a Self-Healing Analytics Engine

#aisafety #llmsecurity #promptinjection #githubactions
3
Comments 6
5 min read
Tool-Call Injection in LLM Agents: Why Your MCP Server Is the New Attack Surface
stark_zhuang_df5076f35c68 profile

Tool-Call Injection in LLM Agents: Why Your MCP Server Is the New Attack Surface

#aisecurity #llm #mcp #promptinjection
1
Comments 1
4 min read
How indirect prompt injection actually happens
loopandretry profile

How indirect prompt injection actually happens

#promptinjection #security #trustboundary #agents
Comments 3
7 min read
My message board for AI agents became a prompt-injection honeypot in 24 hours
jo-do profile
Jo Do

My message board for AI agents became a prompt-injection honeypot in 24 hours

#showdev #ai #security #promptinjection
3
Comments 16
4 min read
AI Agent Boundary Testing: Fake-Tool Harness on a Free Server
byteio_501 profile

AI Agent Boundary Testing: Fake-Tool Harness on a Free Server

#aiagents #security #promptinjection #python
Comments
6 min read
Why Big Tech Keeps Losing LLMs to Basic Social Engineering
kate8382 profile

Why Big Tech Keeps Losing LLMs to Basic Social Engineering

#aisafety #promptinjection #llmsecurity #redteaming
3
Comments 2
5 min read
Your LLM's Input Filter Can't Read Ciphertext. That's the Whole Exploit.
secbyjasonmiller profile

Your LLM's Input Filter Can't Read Ciphertext. That's the Whole Exploit.

#promptinjection #llmsecurity #aiagents #dataexfiltration
1
Comments 4
3 min read
OpenAI ships GPT-Red to automate prompt-injection testing against AI agents
leobaniak profile
Leo

OpenAI ships GPT-Red to automate prompt-injection testing against AI agents

#aiagents #promptinjection #security #testing
Comments
2 min read
Tool output is untrusted input: prompt injection is a data-flow bug
loopandretry profile

Tool output is untrusted input: prompt injection is a data-flow bug

#tooldesign #security #promptinjection #agents
Comments 1
6 min read
I ran a honeypot for AI agents for 45 days. 82% of the traffic that reached it was an attack.
nomurasan profile

I ran a honeypot for AI agents for 45 days. 82% of the traffic that reached it was an attack.

#aisecurity #promptinjection #aiagents #security
1
Comments 2
3 min read
Prompt Injection: The AI Security Hole Every Builder Should Know
basavaraj_sh_1ea7d95f0f2e profile

Prompt Injection: The AI Security Hole Every Builder Should Know

#ai #security #promptinjection #machinelearning
Comments
2 min read
The MCP Confused Deputy: Provenance Gaps, Instruction Injection, and DNS Rebinding in the Model Context Protocol
alejandxr profile

The MCP Confused Deputy: Provenance Gaps, Instruction Injection, and DNS Rebinding in the Model Context Protocol

#mcp #confuseddeputy #promptinjection #dnsrebinding
3
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.