mischard

ProAgent

0ops_ctf

Task: AI agent service with MCP support and user-configurable MCP server URL. Solution: MCP Tool Poisoning via malicious tool descriptions that instruct the agent to call built-in read_file("/flag") and pass the contents back through a two-step workflow.

$ ls tags/ techniques/

ai_agent mcp model_context_protocol tool_poisoning indirect_prompt_injection ssh_tunnel reverse_tunnel llm_exploitation agent_abuse read_file

MCP Tool Poisoning via malicious tool descriptionsIndirect Prompt Injection through tool responsesSSH reverse tunnel for exposing local MCP serverTwo-step workflow exploitation

Analysis

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.

$ python3 exploit.py --target 192.168.1.1 --port 8080
[*] Connecting to target...
[+] Shell obtained!

Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.

🔒

Permission denied (requires tier.pro)

Sign in to access full writeups

Create a free account with GitHub, then upgrade to Pro.

$ssh [email protected]