LLM Attacks (Prompt Injection)

Recursos cross-platform para LLM Attacks (Prompt Injection): máquinas HTB, labs PortSwigger y rooms TryHackMe curados, con writeups validados y skills relacionadas.

​

LLM Attacks (Prompt Injection)

Esta página agrega los recursos para practicar LLM Attacks (Prompt Injection) de forma cross-platform: máquinas retiradas de Hack The Box, labs de PortSwigger Web Security Academy y rooms de TryHackMe, más recursos curados (HackTricks, PortSwigger, etc.) y skills relacionadas.

​

Recursos curados

Fuente	Enlace
PortSwigger	https://portswigger.net/web-security/llm-attacks

​

Labs PortSwigger que practican LLM Attacks (Prompt Injection) (8)

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

​

Rooms TryHackMe que practican LLM Attacks (Prompt Injection) (2)

Room	Dificultad	Tipo	Acceso	Oficial
Advent of Cyber 2024	EASY	Walkthrough	🟢 Free	Abrir
CupidBot	EASY	Challenge	🟢 Free	Abrir

---

← Volver al glosario completo

Última actualización: 2026-05-09