Verified65% 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.
3
Sources
65%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMaliciously crafted tool return values can induce an agent to perform unintended operations, i.e., prompt injection attacks72% similarUnverifiedPrompt injection refers to malicious users inducing an agent to perform operations beyond its intended scope through carefully crafted inputs.72% similarVerifiedJailbreak techniques can be categorized into prompt injection, adversarial prefix attacks, multi-step context construction, and automated jailbreaking.68% similarVerifiedIn multi-agent systems, a compromised agent can deliver malicious messages to other agents via the message board, creating a "lateral propagation" effect.67% similarUnverifiedPrompt Injection ranks first on the OWASP Top 10 risks for AI applications.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/864556API
curl https://kongchang.com/api/v1/knowledge/claims/864556MCP
get_claim(id=864556)