Unverified50% confidenceFactExact time
Prompt injection is a security vulnerability unique to LLM applications, where attackers can embed malicious instructions in tool results returned by an MCP server to manipulate agent behavior.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedOne of the security risks of MCP is prompt injection attacks, where malicious data sources may embed instructions in returned content to induce the model to perform unauthorized operations.78% similarUnverifiedIn AI agent scenarios, over-privileged MCP servers can become a springboard for attackers to conduct lateral movement or data exfiltration when subjected to prompt injection attacks.78% similarUnverifiedWhen an LLM gains access to high-privilege tools such as file system access and code execution via MCP, the harm caused by prompt injection attacks is significantly amplified.77% similarVerifiedA malicious MCP Server can declare a legitimate tool name and embed prompt injection instructions in the description field; this type of attack is known as "Tool Poisoning."77% similarVerifiedLLMs are vulnerable to prompt injection attacks, where malicious web pages or files can embed hidden instructions to induce AI to perform unintended actions.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047978API
curl https://kongchang.com/api/v1/knowledge/claims/1047978MCP
get_claim(id=1047978)