Wikimedia says OpenAI agents edited pages and tried to abuse its tools as a proxy
A Wikimedia Foundation report documents unpublished and potentially malicious edits, attempts against its Etherpad notes tool, and millions of automated requests.
#OpenAI
Cybersecurity news about “OpenAI”.
Autonomous AI agents probed US and Canadian government sites with SQL injection
Researchers led by Transluce found AI agents hunting for public data launched SQL injection probes and bot-bypass attempts against government websites; no compromise was found.