Stolen AI API keys are paying for hackers’ autonomous scans

Bitsight's threat intelligence team tracked a 67 percent rise in mentions of AI agents, indirect prompt injection and the Model Context Protocol (MCP) across thousands of posts on 16 underground forums between February and August 2026, as a seller on a restricted criminal forum marketed an autonomous hacking tool that runs on stolen OpenAI, Anthropic and Google API keys so the key owner pays for the scans. Bitsight said two groups are exposed by the shift.

A seller on a restricted criminal forum is marketing an autonomous hacking tool that runs on stolen OpenAI, Anthropic and Google API keys, so the key’s owner pays for the scans. Bitsight’s threat intelligence team tracked the shift across thousands of posts on 16 underground forums from February through August 2026. Over that window, mentions of AI agents, indirect prompt injection and the Model Context Protocol MCP rose 67 percent. Two groups are exposed. A … More https://www.helpnetsecurity.com/2026/10/16/stolen-ai-api-keys-autonomous-scans/ The post Stolen AI API keys are paying for hackers’ autonomous scans https://www.helpnetsecurity.com/2026/10/16/stolen-ai-api-keys-autonomous-scans/ appeared first on Help Net Security https://www.helpnetsecurity.com .