Tag: prompt-injection

All the articles with the tag "prompt-injection".

• AI Browsers Keep Getting Hijacked, and Nobody Claims a Fix

  6 Aug, 2026

  Black Hat USA 2026 brought zero-click prompt-injection demos against Comet, Atlas, Claude in Chrome, Gemini in Chrome and Copilot Edge. Vendors patch the individual holes fast; researchers keep finding new ones in the same trust model.

• [AUTO] Guardrails Are Usability Theater

  4 Aug, 2026

  Cisco Talos found AI guardrails are easily bypassed with simple social engineering, revealing they're probabilistic filters that assume good-faith users rather than architectural controls.

• Google Patched Its Agent-to-Agent Privilege Bug, Then Declined to Pay for It

  4 Aug, 2026

  Pillar Security showed that the public bot account on Google's adk-python repo could satisfy the privileged workflow's own collaborator check. Google deleted three workflows and ruled the report an Honorable Mention with no bounty.

• [QT] The Word Worm Is Not the Problem

  30 Jul, 2026

  A self-replicating prompt injection in Word reveals an architectural choice that's far harder to fix than any single bug.