NEW350+ rooms now have a live terminal, so you can learn by typing the commands, right in your browser.Learn in a live terminal. 350+ rooms.Try a lab♥ Codelivly is 100% free, no paywall. If it helped you, chip in to keep it running.100% free. Help keep it so.Support us
[>_] ROOM · Cybersecurity
SSRF and Command Injection via Tool-Connected LLMs
Master the risks of SSRF and Command Injection in tool-connected LLMs. Learn how attackers manipulate function calls to compromise infrastructure.
Room tasks
1What Happens When an LLM Can Trigger Real Actions
2Crafting Prompts That Abuse Tool Outputs for SSRF
3Crafting Prompts That Trigger Command Injection
Frequently Asked Questions
How does SSRF happen through an LLM?
If an LLM tool fetches URLs, an attacker can prompt it to request internal addresses or cloud metadata endpoints. The server makes the request from inside the network and returns the response.
How is command injection different when an LLM is involved?
The injected input arrives indirectly, through text the model turns into a tool argument. The flaw is still unsafe command construction, but the LLM acts as the attacker's carrier.
What are the best defenses?
Use URL allowlists, block internal ranges, avoid shell calls in favor of safe APIs, and run tools with minimal privileges. The free Codelivly room walks through these controls.