anthropics / anthropics/claude-code

[Feature Request] Allow adversarial testing and security probing on user-owned projects

Open
#95,701 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

area:model area:security enhancement platform:windows
Dominant language
TypeScript
Stars
147k
Forks
24k
PR merge metrics
PR metrics pending

Description

Bug Description
i have a project that is world-facing (a social network), and have created my own adversarial probe to pen test it, and the platform refuses to work on it. it would seem the highest model is what would be appropriate in this situation, getting downgraded to opus defeats the purpose

Environment Info

  • Platform: win32
  • Terminal: null
  • Version: 2.1.278
  • Feedback ID: 6191409c-e910-4ceb-bfbf-04d0c1094148

Errors

[]

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named. Start by reproducing the refusal with the reported Windows version and feedback ID, then trace where model selection or security probing restrictions are handled; done means user-owned adversarial testing follows a clearly defined policy without the unintended downgrade.

Written by the indexing model from the issue text.

Assessment

Domain
ai, security
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.