AI Security
Today
Practice
Library
Exam
Certificate
Search
⌘K
ខ្មែរ
◐
Sign in
Today
Practice
Library
Profile
Today
Track 418
Agentic AI & Tool Abuse
0 / 4 lessons
Start track
1
Least-Privilege Tool Use for AI Agents
Give the agent a scalpel, not the master key
Advanced
2
Sandboxing Code Execution and Tool Calls
Assume the code an AI writes might be hostile
Advanced
3
Input Validation and Output Filtering
Neither layer alone is enough
Intermediate
4
Rate Limiting and Abuse Prevention
Your API bill is also an attack surface
Intermediate
Agentic AI & Tool Abuse