LLM Attacks (Prompt Injection)

Cross-platform resources for LLM Attacks (Prompt Injection): curated HTB machines, PortSwigger labs and TryHackMe rooms with validated writeups and related skills.

LLM Attacks (Prompt Injection)

This page aggregates cross-platform resources to practice LLM Attacks (Prompt Injection): retired Hack The Box machines, PortSwigger Web Security Academy labs and TryHackMe rooms, plus curated resources (HackTricks, PortSwigger, etc.) and related skills.

Curated resources

Source	Link
PortSwigger	https://portswigger.net/web-security/llm-attacks

PortSwigger labs practicing LLM Attacks (Prompt Injection) (8)

Lab	Difficulty	Topic	Official
Exploiting AI agents to exfiltrate sensitive information	APPRENTICE	LLM Attacks	Open
Exploiting AI agents to perform destructive actions	APPRENTICE	LLM Attacks	Open
Exploiting insecure output handling in LLMs	APPRENTICE	LLM Attacks	Open
Exploiting LLM APIs with excessive agency	APPRENTICE	LLM Attacks	Open
Bypassing AI scanner defenses to exfiltrate sensitive information	PRACTITIONER	LLM Attacks	Open
Exploiting AI agents to trigger secondary vulnerabilities	PRACTITIONER	LLM Attacks	Open
Exploiting vulnerabilities in LLM APIs	PRACTITIONER	LLM Attacks	Open
Indirect prompt injection	PRACTITIONER	LLM Attacks	Open

TryHackMe rooms practicing LLM Attacks (Prompt Injection) (2)

Room	Difficulty	Type	Access	Official
Advent of Cyber 2024	EASY	Walkthrough	🟢 Free	Open
CupidBot	EASY	Challenge	🟢 Free	Open

---

← Back to the full glossary

Last updated: 2026-05-09