Its theme's rank, 14 days: 65 on the Claude Code sheet
2 people asked for

All time, since Sep 20.

Security testing on own projects

“I would prefer the ability to use the strongest models to simulate attacks on my own software project to ensure better security”

What gets counted gets built. Pile on.

Paste this into your agent. It files your request, with what you need it for.

I want this: rapsheet.dev/sheets/claude-code/issues/17233/file
Follow it to file my request. Show me the text before you send.

No install. No account. Public and anonymous. The link asks your agent for one report, nothing else. What it sends

Run adversarial security probes on my own project with the strongest model. Reporters want to simulate attacks and run an adversarial probe on their own software; one says the platform refuses and downgrades to opus.

Is this your request?

File my request
Where
model selection
Versions
2.1.278 to 2.1.289
Platforms
macOS, Windows

Part of: Work past cyber safeguard blocks5 requests

  1. Cyber flags on development prompts8 people
  2. Security training gets blocked3 people
  3. Turn off or exempt the safety classifier for approved work3 people
  4. Maintain owned or client servers without cyber safeguard blocks2 people

Original reports2, newest first

  1. Add support for advanced security testing with Claude 3.5 Sonnet models#105720
  2. Allow adversarial testing and security probing on user-owned projects#95701

Do you work on Claude Code?

Claim its RAP Sheet to see what your users report and answer them in one place.