Unverified50% confidenceFactExact time
Prompt injection refers to malicious users inducing an agent to perform operations beyond its intended scope through carefully crafted inputs.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMaliciously crafted tool return values can induce an agent to perform unintended operations, i.e., prompt injection attacks74% similarUnverifiedPrompt 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.72% similarUnverified在提示词中显式加入自动纠偏指令可以在每个生成步骤中强化对原始约束的注意力权重71% similarUnverifiedMisalignment behaviors in tool-calling agents amplify the leverage of risk because they can trigger external actions such as sending emails, modifying databases, and calling APIs.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/976353API
curl https://kongchang.com/api/v1/knowledge/claims/976353MCP
get_claim(id=976353)