Unverified60% confidenceFactExact time
Prompt Injection refers to attackers using carefully crafted inputs to induce large language models to ignore original system instructions and execute malicious operations; in multi-agent systems, a compromised agent may propagate malicious instructions to other agents through legitimate internal communication channels.
2
Sources
60%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedJailbreak techniques can be categorized into prompt injection, adversarial prefix attacks, multi-step context construction, and automated jailbreaking.68% similarUnverifiedIn multi-agent systems, a compromised agent can deliver malicious messages to other agents via the message board, creating a "lateral propagation" effect.67% similarUnverifiedThe goal of memory poisoning attacks is to embed malicious instructions in an Agent's persistent memory so that it executes unintended operations in future interactions, which differs from the immediate hijacking of prompt injection.66% similarVerifiedJailbreaking refers to an attack technique that bypasses the safety restrictions of large language models by crafting special inputs, with common forms including role-play inducement, multi-turn conversation cumulative bypass, and encoding obfuscation.66% similarUnverified间接提示词注入的攻击链包含四个阶段：植入、触发、执行、外泄63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/864556API
curl https://kongchang.com/api/v1/knowledge/claims/864556MCP
get_claim(id=864556)