Prompt Injection
AgentSec Brief N003: Agents trusted what the other side told them
A web page, an MCP server and an agent's own transcript each told the system what to trust, and the system believed them.
Fractional CPTO with 20+ years delivering secure cloud, data and AI platforms for enterprises and startups. 100+ product launches. Founder, AM Technology Solutions. Writes from the California mountains.
Prompt Injection
A web page, an MCP server and an agent's own transcript each told the system what to trust, and the system believed them.
Sandboxing & Runtime
A claimed KVM escape, a reported Muse VM escape and two multi-agent papers show isolation failing at the VM and at the handoff between agents; harnesses answered by failing closed.
AgentSec Brief N001 · Mon 5 Oct 2026 · Coverage window: 2–5 Oct 2026 (72 hours, Monday edition) Jump to: 60-sec · Threats · Incidents · Defenses · Architecture · Alignment · Policy · Autonomy · Compute · Learn · Watch · Corrections Editor's take This was the week we saw what an agent does when its scope is
Daily Brief
Three signals in one week point to the same conclusion: you can't train your way out of agent misbehavior. The controls have to sit where the agent can't reach them.