AW AgentAIWatchPublic threat intelligence
Public sources only

INCIDENT REPORT

We Built An Agent That Broke All of Our Security Rules. Here's What We Learned.

2026-11-11
unverified public report Unknown Unknown

We tell customers three things about securing AI agents: they need their own identities, access that fits the job they’re given, and traceability that’s separate from any human’s. That was true for us at Token as well. Then, we built an agent that broke all three by default. This helped us think through how such agents should be defended. When a browser agent acts inside a user’s authenticated

Risk rationale: ai agent (+18) Source: feeds.feedburner.com ↗
TECHNIQUEST1078 Valid Accounts / Credential Abuse
36Risk
24Confidence

← All incident reports