Prompt Injection

5 articles about prompt injection.

Prompt Injection Through Tool Results: The Hidden Attack Vector

·3 min read

How tool results become prompt injection vectors for AI agents, and why system prompts are your best defense against malicious content in API responses.

prompt-injectionsecuritytool-resultssystem-promptagent-security

Special Token Injection Attacks on AI Coding Agents

·3 min read

Gaslighting LLMs with special token injection is a real threat to AI coding agents. Learn how these attacks work and how to defend your agent workflows.

securityprompt-injectionai-agentscode-reviewllm-attacks

AI Agent Security Is Backwards - Why Input Validation Matters More Than Output Verification

·2 min read

Most AI agent security focuses on verifying outputs - did the click land correctly? But unsigned, unvalidated inputs are the real attack surface.

ai-safetyagent-securityinput-validationdesktop-agentprompt-injection

MEMORY.md as an Injection Vector - The Security Risk of Implicitly Trusted Config Files

·3 min read

CLAUDE.md and MEMORY.md files are loaded every session and trusted implicitly by AI agents. This makes them a potential prompt injection vector that most

securityprompt-injectionmemoryclaude-mdconfig-filesai-agent

Prompt Injection and AI Agents - Why Browser-Based Agents Have a Bigger Attack Surface

·3 min read

AI agents that run inside the browser inherit whatever the page feeds them, including injection payloads. Native agents that interact from outside have a

securityprompt-injectionbrowser-agentsnative-agentsai-safety

Browse by Topic