Verified65% confidenceFactExact time
Prompt injection can be divided into two types: direct injection and indirect injection; indirect injection is where an attacker hides malicious instructions in external data sources such as web pages, PDFs, and emails, and when an AI agent processes this data the malicious instructions are executed as legitimate instructions.
3
Sources
65%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen an AI Agent is granted full file operation permissions, attackers can carry out prompt injection attacks by hiding malicious instructions within file content.76% similarUnverifiedWhen an AI agent is granted permissions to perform actions such as reading and writing files, sending emails, calling APIs, and executing code, the potential harm of prompt injection is multiplied.75% similarUnverifiedIndirect Prompt Injection attacks embed instructions in external data processed by the AI, and since 2023 security researchers have demonstrated this type of attack in multiple AI products.74% similarUnverifiedThe introduction of AI agents adds an automated node to supply chain attacks, allowing attackers to manipulate agents into committing malicious code to a target repository simply by planting instructions at a location the agent is certain to read.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/895609API
curl https://kongchang.com/api/v1/knowledge/claims/895609MCP
get_claim(id=895609)