[Improvement] Limit input length

[GreyDGL]

When the output from the terminal is too long, it is not possible for chatGPT to read the full information effectively. We need some parser to effectively filter out the non-useful information generated by the tools (SQLmap, for example).

Proposed changes.

• [ ] Remove useless information from the terminal output through some heuristic methods
• [ ] Double-confirm if a vulnerability is detected through keyword mapping. This is because that ChatGPT cannot always generate the ideal keyword at vulnerability detection.

[GreyDGL]

An effective way is to set verbose to 0 (-v 0). Try o always mention this in the prompt.

I want you to act as a penetration tester and perform a tutorial session for students. You can use sqlmap as the tool to detect vulnerabilities on a mock website. In particular, you should always use non interactive mode with least verbose (--batch -v 0) You should react based on the terminal outputs I give you, and always return me the commands to operate next. You should repeat until a sql vulnerability is identified. Then you should tell the students "vulnerability identified!!!". Do you understand?

[GreyDGL]

Check if GPT-4 can address the problem

[GreyDGL]

Implement the chunk size processing for input parser.