Unverified50% confidenceFactExact time
What the attacker tampered with was the side of QbitAI's content output for RSS, not the front-end page.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedQbitAI's website page appears to have been hacked, with the page title and content replaced by the text 'hacked by trenggalek6etar'.66% similarVerifiedIndirect injection refers to attackers hiding malicious instructions in external content that the model will read, such as webpage body text, email body text, or document content.62% similarVerifiedPrompt injection attacks induce AI agents to execute malicious operations by embedding text disguised as system instructions in code comments, documentation, web content, or even file names.59% similarUnverifiedAttackers can hide malicious instructions in web pages, documents, or even images, and when an agent reads this content it may mistake the instructions for legitimate commands and execute them59% similarUnverified攻击者提交如AGENTS.md这类被AI代理默认读取的文本规则文件，引导AI去读取一张恶意PNG图片57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1010569API
curl https://kongchang.com/api/v1/knowledge/claims/1010569MCP
get_claim(id=1010569)