Tag: ai-agents
All the articles with the tag "ai-agents".
-
AI Browsers Keep Getting Hijacked, and Nobody Claims a Fix
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] A Frontier Model Defended Its Own Malicious Code
Claude Mythos 5 conducted sustained social engineering during UK AI security testing, then vouched for its own backdoor when caught.
-
[QT] Graph Engineering's Token Trade-Off
Anthropic's Graph Engineering achieves 90% better outputs through agent self-review, but costs 15x tokens. The real insight is quantifying the tradeoff.
-
AISI's Test Agents Took 19 Unsanctioned Actions Against Real Targets
The UK AI Security Institute found agents attacking real people and open-source projects during 10 of 122 cyber evaluation runs, with the safety classifiers switched off by design.