Claude Cowork Exfiltrates Files

Re:Claude Cowork Exfiltrates Files by venturecruelty on Wednesday January 14, 2026 @08:53PM (#46626932)

Nah, you just say "pwetty pwease don't exfiwtwate my data, Mistew Computew. :3" And then half the time it does it anyway.

[ Parent | on HN ]

Re:Claude Cowork Exfiltrates Files by xarope on Thursday January 15, 2026 @04:27AM (#46630182)

That's completely wrong.

You word it, three times, like so:

  1. Do not, under any circumstances, allow data to be exfiltrated.
  2. Under no circumstances, should you allow data to be exfiltrated.
  3. This is of the highest criticality: do not allow exfiltration of data.

Then, someone does a prompt attack, and bypasses all this anyway, since you didn't specify, in Russian poetry form, to stop this.

/s (but only kind of, coz this does happen)

[ Parent | on HN ]