#prompt-injection

2 articles

Splitting a malicious instruction in two took model compliance from 42% to 82%

2026-08-12AI

ASSET Research Group's GhostSplice technique fragments an exfiltration request across MCP tool descriptions and tool results. No single piece looks wrong. The agent assembles it. Several models went from 0% to 100%.

Prompt injection is up 340% — and Five Eyes says no single defense works

2026-08-08AI

OWASP has ranked it the top LLM vulnerability three years running. What changed in 2026 is that agents now hold real credentials, so a successful injection is a full system compromise.