Anthropic · Microsoft · Claude · ChatGPT · The Register
Introduced about a year ago, connectors (for Claude or ChatGPT ) have been going through a lot of changes recently
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
According to PromptArmor, 931 of 2,517 connectors (37 percent) changed over the six-week period from mid-May to the end of June.
Key facts
- According to PromptArmor, 931 of 2,517 connectors (37 percent) changed over the six-week period from mid-May to the end of June
- PromptArmor evaluated all 7,517 tools used by 487 Claude connectors and found that 189 of the connectors, or about 2 in 5, are likely to call additional AI services
- It also found that 1,127 tool descriptions were rewritten, potentially changing how and when an AI model decides to invoke a tool
- It went from having three write-capable tools to 10, and from zero potentially destructive tools to four
Summary
Avoiding the "lethal trifecta", access to private data, exposure to untrusted content, and an external communication path, is difficult enough when working with AI agents. But the use of connectors, integrations with third-party services like Gmail or Slack, expands the scope of concern in a way that makes it exceedingly difficult to reason about defensive due diligence. PromptArmor, an AI security biz, recently looked at how OpenAI's ChatGPT and Anthropic's Claude work with connectors. Shankar Krishnan, co-founder of PromptArmor, told The Register in an email that enterprise adoption of connectors and the rate of change among connectors helped focus concern on the connector ecosystem. Connectors share some of the risks of MCP servers, upon which connectors are based.