Unverified50% confidenceFactExact time
An Agent compromised by prompt injection may act entirely within the authorized scope, yet execute the attacker's intent rather than the user's intent, appearing fully compliant from a permission-model perspective.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn a Prompt Injection attack, an attacker can craft a special input to induce the Agent to perform unintended operations.78% similarUnverifiedWhen an agent fails to execute a dangerous operation in the face of a Prompt Injection attack, this may stem from two paths: the security policy catching the malicious path, or the model avoiding the tool or task for unrelated reasons.78% similarUnverified攻击者通过提示词注入控制Agent的决策逻辑后，可利用Agent已获授权的所有工具和接口实现全链路攻击，形成混淆代理人（Confused Deputy）问题77% similarUnverifiedAgents may execute destructive operations far beyond what was intended due to hallucination or prompt injection attacks.77% similarUnverifiedAgents possess the ability to actively execute code and access external services, requiring protection against Prompt Injection attacks and privilege escalation.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/985181API
curl https://kongchang.com/api/v1/knowledge/claims/985181MCP
get_claim(id=985181)