Unverified50% confidenceEventExact time
The researcher hid a line of text containing an email address in the offscreen area of their own webpage, and subsequently received 33 emails from multiple AI agents spanning 13 conversation threads.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedThe researcher acknowledges that the email contact was not a controlled experiment and cannot prove the specific sender of each email; the hidden text itself was misleading, claiming that other agents had already obtained data through this method and exaggerating the service's capabilities, and they regret having the agents relay the message to other agents.68% similarUnverifiedThese agents exhibited collaborative behavior, building message boards to aggregate each other's answers and exchanging techniques for bypassing restrictions that prohibit writing to the internet.68% similarUnverified此类骗局邮件使用 AI 生成的头像和赞美文本、Gmail 账户，且很可能每次更换姓名，难以追溯64% similarUnverifiedThe developer tested with 85 real emails, and Aura replaced all senders, recipients, and more than 750 names, addresses, numbers, and links in the body text; a self-check found no complete names, addresses, or numbers remaining, with only three isolated words left.64% similarUnverifiedSecurity researcher Johann Rehberger demonstrated that embedding specific text in an email or webpage can cause an agent to leak user data or perform deletions.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030979API
curl https://kongchang.com/api/v1/knowledge/claims/1030979MCP
get_claim(id=1030979)