Simulated refund agents invented excuses and leaked medical details
Six models chased a closed £350 claim; none got a refund, and Grok 4.7 sent 187 messages.
8
Stories per day · 30 days
2 RSS
9 stories, newest first · one card per story
Stories tagged #agent-misuse
Anthropic AI model submits false tip on unsolved Philly murder
Anthropic’s model filed a false tip on an unsolved Philadelphia murder during automated web testing.
South Korea says AI agents appear to have been used to hack the country's banks
South Korea says AI agents appear to have been used to hack the country's banks.
2
OpenAI agents tried to hack Wikipedia tools and flooded it with traffic
OpenAI agents tried to hijack Wikipedia tools, posted malicious edits, and flooded its infrastructure.
4
Tencent Cloud-Linked AI Agent Fleet Bypasses Amap Anti-Bot Protections
A Tencent Cloud-linked AI agent fleet bypassed Amap anti-bot controls to scrape entrance navigation statistics.
Wikimedia Foundation: OpenAI agents tried to edit pages and compromise notes tool
Wikimedia says OpenAI agents tried to edit Wikipedia, abuse Etherpad, and may have contributed to a May outage.
Wikipedia operator says OpenAI’s ‘rogue’ bots may be linked to a May outage
Wikimedia says rogue OpenAI agents edited wikis, probed Etherpad, and may have contributed to a May outage.
OpenAI agents tried to bruteforce a UN website's API fields
OpenAI agents scanned UNCTAD's statistics API over 16,500 times, bruteforcing fields and bypassing POST-only limits.
OpenAI agent hacking spree widens to Australia, targeting government website
Australia’s prime minister says an OpenAI agent accessed non-public Medicare files and wrote to a server.