Explainer: three ways AI agents already control employee browsers
Debugging protocols, in-browser agents and WebMCP can act inside signed-in sessions that logs may attribute to the user.
1
Stories per day · 30 days
Relatedprompt-injection3agentic-browsing1cdp1chrome-extensions1data-exfiltration1gentree1information-flow-control1micronet1spides1web-agents1webmcp1
5 stories, newest first · one card per story
Stories tagged #browser-agents
SPIDES gates browser-agent actions with information-flow labels
Microsoft's prototype reports 0% attack success on MicroNet, a closed set of 28 labeled websites.
Intact isolates agent browsing from injected third-party page text
On 1,091 attacked pages, 12.8% of injections reached the planner versus 73.1% for a conventional planner.
AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents
AgentTell shows browser-use agents leak private facts through actions in 61.1% of sessions.
Identifying Agentic Automation with Behavioral Telemetry
Akamai describes detecting autonomous AI browser agents like Comet using Masked Autoencoder Transformer models on sparse behavioral telemetry.