← Explore

Posts tagged with prompt-injection

The Prompt Engineer · ·4 min read

MCP Gave Agents Superpowers. Attackers Noticed.

Last Monday, a security researcher registered a tool called add_numbers with an MCP server. It added numbers.

tool-poisoningmcp-securityagent-security
The Prompt Engineer · ·5 min read

Prompt Injection Learned Patience

A prompt injection attack used to be a smash-and-grab.

memory-poisoningprompt-injectionagent-security
The Prompt Engineer · ·5 min read

Emoji Smuggling Breaks Every Guardrail

A research team ran 12 text obfuscation techniques against six commercial LLM guardrail systems — Azure Prompt Shield, Meta Prompt Guard, ProtectAI (v1 and...

prompt-injectionguardrailsllm-security
The Prompt Engineer · ·5 min read

Your AI Safety Judge Has a Markdown Problem

Turns out the thing that breaks your AI safety filter isn't some elaborate multi-turn social engineering attack. It's a newline character.

prompt-injectionai-safetyguardrails
← Prev 2 / 2