PortSwigger Walkthrough - Exploiting AI agents to perform destructive actions
Walkthrough of PortSwigger's 'Exploiting AI agents to perform destructive actions' lab.
Write-ups / Tag
web-llm
7 write-ups with this tag.
PortSwigger Walkthrough - Exploiting AI agents to exfiltrate sensitive information
Walkthrough of PortSwigger's 'Exploiting AI agents to exfiltrate sensitive information' lab.
PortSwigger Walkthrough - Exploiting AI agents to trigger secondary vulnerabilities
Walkthrough of PortSwigger's 'Exploiting AI agents to trigger secondary vulnerabilities' lab.
PortSwigger Walkthrough - Exploiting LLM APIs with excessive agency
Walkthrough of PortSwigger's 'Exploiting LLM APIs with excessive agency' lab.
PortSwigger Walkthrough - Bypassing AI scanner defenses to exfiltrate sensitive information
Walkthrough of PortSwigger's 'Bypassing AI scanner defenses to exfiltrate sensitive information' lab.
PortSwigger Walkthrough - Exploiting vulnerabilities in LLM APIs
Walkthrough of PortSwigger's 'Exploiting vulnerabilities in LLM APIs' lab.
PortSwigger Walkthrough - Indirect prompt injection
Walkthrough of PortSwigger's 'Indirect prompt injection' lab.