Unverified60% confidenceFactTime unknown
VS Code requires users to explicitly authorize the Agent to execute system commands through a pop-up permission notification.
2
Sources
60%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBecause an Agent makes its own decisions, it is advisable to grant it only the tool permissions it truly needs, and it must request user confirmation before performing sensitive operations such as deleting files or transferring money.74% similarUnverifiedResponsibilities should be separated between the Agent (responsible for proposing, with no sending or credential modification) and the Executor (responsible for acting, only running proposals marked as approved and atomically checking status).73% similarUnverifiedHuman approval should be retained for irreversible Agent operations (such as sending, paying, deleting), because the division of labor in which the model decides and the application executes means permission control falls entirely at the application layer.73% similarUnverifiedPrompt engineering for production-grade Agents requires adding constraints, otherwise the Agent may perform sensitive operations (such as sending emails) without approval.73% similarUnverifiedIn multi-agent architectures, messages sent from one agent to another should be protected in the same way as user input, and each agent should only possess the permissions necessary to run its tools.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40421API
curl https://kongchang.com/api/v1/knowledge/claims/40421MCP
get_claim(id=40421)