Unverified50% confidenceCautionExact time
Prompts are not an access control mechanism, and system prompts alone cannot reliably enforce application permission rules.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSystem prompts are guidance, not a permission system; permissions must be enforced where the model cannot talk its way around them, namely at runtime rather than in the prompt.79% similarUnverifiedUser-defined rules are injected into the system as constraints and can only make the policy stricter, not relax permissions.76% similarUnverifiedThe focus of defending against indirect prompt injection cannot be on 'identifying malicious text' but must be on capability constraints—even if the agent is persuaded to call a tool, the system should have the authority to refuse that call.70% similarUnverifiedPermission checks must exist in code that the model cannot bypass through reasoning; alignment techniques should not serve as the control plane.70% similarUnverifiedA prompt is essentially a request that can be ignored or bypassed, so it cannot serve as a security constraint mechanism for an Agent.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1048038API
curl https://kongchang.com/api/v1/knowledge/claims/1048038MCP
get_claim(id=1048038)