DEV Community

AI Security Digest Series' Articles

Back to Felipe 0liveira's Series
When Agents Overreach — This Week's LLM Security News Is All About Tool-Calling Gone Wrong

When Agents Overreach — This Week's LLM Security News Is All About Tool-Calling Gone Wrong

Comments
5 min read
Stacking Guardrails Won't Save You — This Week's AI Security Research Proves It Again

Stacking Guardrails Won't Save You — This Week's AI Security Research Proves It Again

Comments
6 min read
The Guardrail Gap — MCP Filesystem Leaks, a Copilot RCE, and Agent Guards That Miss Non-English Attacks

The Guardrail Gap — MCP Filesystem Leaks, a Copilot RCE, and Agent Guards That Miss Non-English Attacks

Comments 3
7 min read
The Channel Nobody's Watching: MCP Leaks, Poisoned Skill Files, and a Live Agent Incident

The Channel Nobody's Watching: MCP Leaks, Poisoned Skill Files, and a Live Agent Incident

1
Comments 1
8 min read
Your Guardrails Are Now the Attack Surface — and the Threat Moved Below the Prompt

Your Guardrails Are Now the Attack Surface — and the Threat Moved Below the Prompt

Comments
6 min read