Verified75% confidenceOpinionExact time
Internal agents that are maliciously prompt-injected or misled may execute dangerous operations while holding legitimate permissions.
3
Sources
75%
Confidence
Long-term
Relevance
8/16/2026
First Seen
Sources
AI智能体挖出SharePoint高危漏洞：运行时零可见性才是真正隐患
Related Claims
UnverifiedTool calls introduce the Confused Deputy problem: the agent holds legitimate credentials and, once induced, will use its own credentials to perform unauthorized operations on behalf of the attacker.74% similarUnverifiedWhen a proactively executing agent makes an error (such as automatically publishing incorrect content), the consequences are more severe than those of a passive tool, placing extremely high demands on alerting and manual confirmation mechanisms.74% similarUnverifiedSelf-generated prompt injection is a security risk in which the injected instruction originates from the model itself rather than an external attacker.73% similarUnverifiedIf an AI agent inherits administrator permissions, a single prompt injection attack or an erroneous instruction caused by model hallucination could result in catastrophic consequences.73% similarUnverifiedPrompt injection requires deceiving the AI rather than humans, bypassing security measures designed for people, and an innocuous request such as asking an AI assistant to organize an inbox is sufficient to trigger the attack.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/756994API
curl https://kongchang.com/api/v1/knowledge/claims/756994MCP
get_claim(id=756994)