Prompt Injection Defense 콘텐츠 아카이브

총 14개 · 1 / 1페이지

  1. Comment and Control: one PR title stole three agents' keys
  2. Zero-click email, zero model-level fix: what EchoLeak taught us about output filtering
  3. One click owns your agent: the ClawHavoc MCP supply chain attack and how to harden against it
  4. Your model scored 2.7% on jailbreak benchmarks — and still broke at turn 8
  5. Your agent read that file. Now it's infected.
  6. Your agent's memory outlives the session. So does the attack.
  7. Gaslight tricks the analyst, not the sandbox
  8. DuneSlide turns paths into RCE
  9. Ghostcommit hides orders in PNGs
  10. LogInject turns security logs into dormant prompt injections
  11. A fake approval made five CI/CD agents ship clean-looking malicious code
  12. A Word file can turn Copilot into a prompt worm — ship this boundary
  13. A public issue triggered a maintainer agent — ship this handoff gate
  14. One skill can make a correct task 92% slower — ship this trajectory gate

디스커버 페이지에서 더 많은 채널 살펴보기