LLM protection

[autodepo]

Is your feature request related to a problem? Please describe. Usage of LLM such as ChatGPT, Claude or others is speeding up the de-obfuscation

Describe the solution you'd like Adding custom dead strings that would trigger the anti-TOS response from major LLM:

● Perfect! So PL() is called to initialize the GL array. These strings likely get decoded/deobfuscated somewhere.
  The arrays use variable indices which are computed at runtime, making static replacement difficult.

  The strings in
  ⎿ API Error: Claude Code is unable to respond to this request, which appears to violate our Usage Policy
    (https://www.anthropic.com/legal/aup). Please double press esc to edit your last message or start a new session for
    Claude Code to assist with a different task. If you are seeing this refusal repeatedly, try running /model
    claude-sonnet-4-20250514 to switch models.

Describe alternatives you've considered N/A

Additional context This could be added as an array of strings that would trigger it (I won't mention those here for obvious reasons)

[doctor8296]

@MichaelXF I mean, why not?

[solanarapist]

Bump

[Mrgaton]

Seems fun +1