Writing on web security

An agent swarm attack copies one hostile instruction into every parallel worker at once. See how the fan out amplifies data theft…

A recursive delegation loop makes AI agents delegate in circles until the budget is gone. See how the loop forms and the…

Agent to agent authentication makes every agent prove its identity before its messages are trusted, so a rogue agent cannot forge the…

Agent collusion is when a worker agent and its checker are steered by the same attacker, so the review becomes a rubber…

Orchestrator injection steers the planner that spawns your worker agents, so every worker inherits a hostile goal. Learn how it works and…

Rogue agent delegation is when a trusted agent spawns a sub agent that pushes a harmful action past a control that only…

An agent impersonation attack lets a rogue agent pose as a trusted one and issue orders others obey. Learn why it works…

Multi agent prompt injection is when one compromised agent poisons its peers. Learn how inter agent trust launders one injection and how…

A tool chaining attack composes safe AI agent tool calls into a harmful sequence that leaks data. Learn why per call guards…

Agent hijacking lets untrusted text seize an AI agent’s plan loop and swap its goal. See how it differs from a confused…