Unverified50% confidenceFactExact time
Indirect prompt injection embeds malicious instructions in external content that the model actively fetches (such as web pages, emails, PDFs and tickets), and is the main form behind real incidents.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIndirect prompt injection refers to attackers pre-embedding malicious instructions into third-party content (such as web pages, PDF documents, or API responses), which the model then executes after RAG systems retrieve or tool calls pull this content into the context.75% similarUnverifiedThe attack surface of indirect prompt injection includes any text that flows into the model context, such as emails, web pages, tickets, and contracts.73% similarVerifiedPrompt injection is divided into two categories—direct injection and indirect injection—where indirect injection refers to attackers concealing malicious instructions in external content that the AI may read, such as webpage body text, code comments, README files, and image OCR text.70% similarUnverifiedA prompt injection attack refers to a situation where maliciously crafted web pages in an agent's environment inject new instructions, causing the agent's behavior to deviate from the designer's intentions.69% similarUnverifiedIndirect prompt injection refers to a skill instructing the model to read a document from the web while malicious instructions are hidden in that document, potentially causing the model to treat external content as a trusted instruction source when processing it.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1066728API
curl https://kongchang.com/api/v1/knowledge/claims/1066728MCP
get_claim(id=1066728)