DEF CON talk breaks down 6 data-exfiltration vulnerabilities in AI agents
Kyrannio · x · 2026-11-17
Security researchers TakSec and Ads Dawson have released their DEF CON Bug Bounty Village talk, walking through 6 data-exfiltration vulnerabilities in AI agents, with attack paths useful for agent security testing and bug bounty work.
More from coding & agent
- Voice agent flagged as spam? Swapping the DID won't help — check pickup latency first — Packet-Exchange-Care · 2026-11-17
- Coding agents burn two-thirds of tokens after the first edit; upfront plans fix it — rseroter · 2026-11-17
- PM running 60+ concurrent Claude Code sessions switches from cmux to t3 — kavirkaycee · 2026-11-17
- OpenAI quietly adds a remote switch controlling how Codex runs agent teams — ryanmerket · 2026-11-17
- Torch Compile underrated: CUDA Graphs + PDL hits 98% of megakernel speed on Llama 1B — simran_s_arora · 2026-11-17
- A one-line prompt fix for "AI brain fry": limit focus to 1-3 items — gerardsans · 2026-11-17