Verified65% confidenceFactExact time
Indirect 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.
3
Sources
65%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedPrompt 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.80% similarVerifiedIndirect Prompt Injection is the most harmful variant of Prompt Injection, where an attacker plants hidden instructions on a public page to have an agent execute them.76% similarUnverifiedIndirect prompt injection does not require an attacker to have direct access to the agent; it only requires poisoning a data source that the agent will actively read.75% 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74% 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 them74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958268API
curl https://kongchang.com/api/v1/knowledge/claims/958268MCP
get_claim(id=958268)