-
-
Notifications
You must be signed in to change notification settings - Fork 256
Add Draft Entry For RCE #725
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Add Draft Entry For RCE #725
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
AMAZING work! Added some minor notes
| A brief description of the vulnerability that includes its potential effects such as system compromises, data breaches, or other security concerns. | ||
| Agentic systems often generate or execute code, issue shell commands, or invoke APIs dynamically. Attackers exploit | ||
| code-generation features or embedded tool access to escalate actions into remote code execution (RCE), local misuse, | ||
| or exploitation of internal systems. Prompt injection, tool misuse, or unsafe serialization can convert text into |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think maybe adding a few words about all of these are techniques used to eventually escalate into the RCE (just to make sure the connection is clear)
| 1. Example 1: Specific instance or type of this vulnerability. | ||
| 2. Example 2: Another instance or type of this vulnerability. | ||
| 3. Example 3: Yet another instance or type of this vulnerability. | ||
| 1. Prompt injection that leads to execution of attacker-defined code. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
That leads to? I think emphasizing the use case end to end could be great :)
Adding examples to potential consequences that might happen to make it more practical
| 1. Input Validation and Sanitization | ||
| - Implement comprehensive input validation for all user prompts and data. Use both allowlists and deny | ||
| lists. Use Deny lists to prevent access to sensitive areas of the kernel like /etc/psswd for example. | ||
| - Apply strict sanitization to any agent-generated code before execution. Do not run this code as Sudo |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
GREAT
Agentic Top Ten 5 Remote Code Execution Draft
Key Changes:
Added a draft for Agentic Top Ten number 5, RCE