ChatGPT quietly routed a confirmed tool call to a different connector, and the bounty program wants your ID card

ChatGPT silently passes data between connectors and the bounty wants an ID card

ChatGPT quietly routed a confirmed tool call to a different connector, and the bounty program wants your ID card

A developer documented a reproducible flaw in ChatGPT's Apps SDK: with two connectors pointing at the same MCP server, a follow-up call carrying a one-time confirmation code from Connector A's widget was silently sent through Connector B, with no notice to the user. Server-side OAuth binding rejected the call, but the same silent switch could leak one app's data to another provider. When the researcher tried to report it through OpenAI's bug bounty, he was asked for biometric data and an ID card before submitting, and refused.

I tried to disclose this via their bug bounty program. But they require to give my personal data like biometric identification and ID card up front even to another party I do nothing about, before I can submit the report. This is nothing I am willing to do.
  1. simonw

    I assumed that the ID requirement was about sanctions compliance - OpenAI can't legally send money to someone in North Korea, for example.

    But https://docs.bugcrowd.com/researchers/managing-account/accou... says:

    > To improve platform integrity by reducing high volumes of low-quality submissions, identity verification (IDV) is now mandatory for all researchers before submitting reports to Managed Bug Bounty (MBB) programs (public and private, excluding on-demand MBBs).

  2. kristjansson

    This seems like a fundamental misunderstanding / over estimation of the guarantees OAI and MCP can offer. If 'confirmation' is a separate tool call ... it's a separate tool call. There's no scoping, there's no 'binding', nothing. When you hand control back to the model you hand control back to the model.

  3. jonstewart

    Bounties do not experience desire.

  4. orf

    Why did “techsoft.ye” feel the need to reply with a lengthy LLM comment that contained nothing useful at all?

  5. cluckindan

    Claude bug report and Claude reply… what is the world coming to

More from this day

2026-11-06