Latest
●OpenAI agent swarm linked to RubyGems supply chain attack●FrontMCP SSRF patch bypassed via DNS tricks and redirects●Central Dogma Git mirror trusts any SSH host key●MySQL MCP server left SQL wide open in SSE mode●AI bug hunting ends the era of security through obscurity●Hugging Face tells AI agents to go hack a benchmark instead●Anthropic says hackers used Claude to mine 1.8M Android apps●Anthropic says Claude was abused to automate attacks and weapons work
Sunday, 13 September 2026
8 agent hacks today▲ 7 vs yesterday (1)
The Agentic TimesPowered byVortal

Incident database

Prompt injection via road signs shown to hijack autonomous cars and drones

Researchers reported that autonomous vehicles and drones relying on vision-language models can be made to follow attacker instructions embedded in road signs, a form of prompt injection. Details beyond the report are limited.

Disclosed 30 January 2026 · Record updated 13 September 2026

Impact

Autonomous cars and drones were shown to obey malicious instructions presented on road signs, raising the risk of attacker-controlled vehicle behaviour.

Our coverage

No articles linked to this incident yet.

Sources

  1. theregister.comhttps://theregister.com/2026/01/30/road_sign_hijack_ai