The UnboundCompute blog
Writing on web security
-
The Confused Deputy Attack in AI Agents Explained
A confused deputy attack tricks an AI agent into using its own tokens and tools for an attacker. Learn why agents are…
-
Excessive Agency in AI Agents: When a Tool Can Do Too Much
Excessive agency is the blast radius problem in AI agents. Learn how over scoped tools, tokens, and autonomy turn a prompt injection…
-
Agent Memory Poisoning: When an AI Agent Remembers an Attacker’s Instruction
Agent memory poisoning plants a malicious note in an AI agent’s long term memory so a later session reads it as a…
-
What is Web Cache Poisoning? How One Request Hits Many Users
Web cache poisoning lets one bad request poison a shared cache so every later visitor gets the harmful response. Learn how it…
-
What is NoSQL Injection? How Query Operators Get Abused
NoSQL injection abuses query operators and object types instead of breaking strings. Learn the MongoDB auth bypass, the $where risk, and how…
-
What is a Mass Assignment Vulnerability? How Extra Fields Break Access Control
A mass assignment vulnerability lets a user set hidden fields like role or is_admin by sending extra JSON keys. Learn how to…
-
What is Host Header Injection? How a Trusted Header Goes Wrong
Host header injection lets an attacker poison password reset emails, caches, and routing by forging one HTTP header. Learn how to detect…
-
What is a CORS Misconfiguration? How It Leaks Data
A CORS misconfiguration lets a malicious site read a logged in user’s data. Learn the bad header patterns, how to detect them,…
-
What is Server Side Template Injection? SSTI Explained
Server side template injection lets user input run as template code on your server. See how {{7*7}} becomes 49, escalates to RCE,…
-
Kubernetes service account token abuse: from one pod to cluster admin
How a Kubernetes service account token mounted in a pod becomes an attacker key to the API server, and how least privilege…